firefrost-gaming/antigravity-skills-reference
3
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat: add in-app Sync Skills button and simplify START_APP.bat launcher

Browse Source
This commit is contained in:
Zied
2026-03-02 09:56:15 +01:00
parent c9a76a2d94
commit b42ab600ec
3329 changed files with 329667 additions and 4115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
.DS_Store vendored Normal file
View File

Binary file not shown.

2
.github/workflows/ci.yml vendored
View File

@@ -50,6 +50,8 @@ jobs:
continue-on-error: true
- name: Run tests
env:
ENABLE_NETWORK_TESTS: "1"
run: npm run test
- name: 📦 Build catalog

1
.gitignore vendored
View File

@@ -2,6 +2,7 @@ node_modules/
__pycache__/
.ruff_cache/
.worktrees/
.tmp/
.DS_Store
# npm pack artifacts

506
CATALOG.md
View File

File diff suppressed because it is too large Load Diff

47
CHANGELOG.md
View File

@@ -7,6 +7,49 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
---
## [6.7.0] - 2026-03-01 - "Intelligence Extraction & Automation"
> **New skills for Web Scraping (Apify), X/Twitter extraction, Genomic analysis, and hardened registry infrastructure.**
This release integrates 14 new specialized agent-skills. Highlights include the official Apify collection for web scraping and data extraction, a high-performance X/Twitter scraper, and a comprehensive genomic analysis toolkit. The registry infrastructure has been hardened with hermetic testing and secure YAML parsing.
## 🚀 New Skills
### 🕷️ [apify-agent-skills](skills/apify-actorization/)
**12 Official Apify skills for web scraping and automation.**
Scale data extraction using Apify Actors. Includes specialized skills for e-commerce, lead generation, social media analysis, and market research.
### 🐦 [x-twitter-scraper](skills/x-twitter-scraper/)
**High-performance X (Twitter) data extraction.**
Search tweets, fetch profiles, and extract media/engagement metrics without complex API setups.
### 🧬 [dna-claude-analysis](skills/dna-claude-analysis/)
**Personal genome analysis toolkit.**
Analyze raw DNA data across 17 categories (health, ancestry, pharmacogenomics) with interactive HTML visualization.
---
## 📦 Improvements
- **Registry Hardening**: Migrated all registry maintenance scripts to `PyYAML` for safe, lossless metadata handling. (PR #168)
- **Hermetic Testing**: Implemented environment-agnostic registry tests to prevent CI drift.
- **Contributor Sync**: Fully synchronized the Repo Contributors list in README.md from git history (69 total contributors).
- **Documentation**: Standardized H2 headers in README.md (no emojis) for clean Table of Contents anchors, following Maintenance V5 rules.
- **Skill Metadata**: Enhanced description validation and category consistency across 968 skills.
## 👥 Credits
A huge shoutout to our community contributors:
- **@ar27111994** for the 12 Apify skills and registry hardening (PR #165, #168)
- **@kriptoburak** for `x-twitter-scraper` (PR #164)
- **@shmlkv** for `dna-claude-analysis` (PR #167)
---
## [6.6.0] - 2026-02-28 - "Community Skills & Quality"
> **New skills for Android UI verification, memory handling, video manipulation, vibe-code auditing, and essential fixes.**
@@ -39,6 +82,10 @@ Check prototypes and generated code for structural flaws, hidden technical debt,
## 📦 Improvements
- **Skill Description Restoration**: Recovered 223+ truncated descriptions from git history that were corrupted in release 6.5.0.
- **Robust YAML Tooling**: Replaced fragile regex parsing with `PyYAML` across all maintenance scripts (`manage_skill_dates.py`, `validate_skills.py`, etc.) to prevent future data loss.
- **Refined Descriptions**: Standardized all skill descriptions to be under 200 characters while maintaining grammatical correctness and functional value.
- **Cross-Platform Index**: Normalized `skills_index.json` to use forward slashes for universal path compatibility.
- **Skill Validation Fixes**: Corrected invalid description lengths and `risk` fields in `copywriting`, `videodb-skills`, and `vibe-code-auditor`. (Fixes #157, #158)
- **Documentation**: New dedicated `docs/SEC_SKILLS.md` indexing all 128 security skills.
- **README Quality**: Cleaned up inconsistencies, deduplicated lists, updated stats (954+ total skills).

100
README.md
View File

@@ -1,6 +1,6 @@
# 🌌 Antigravity Awesome Skills: 954+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
# 🌌 Antigravity Awesome Skills: 968+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
> **The Ultimate Collection of 954+ Universal Agentic Skills for AI Coding Assistants — Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode, AdaL**
> **The Ultimate Collection of 968+ Universal Agentic Skills for AI Coding Assistants — Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode, AdaL**
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-Anthropic-purple)](https://claude.ai)
@@ -17,7 +17,7 @@
If this project helps you, you can [support it here](https://buymeacoffee.com/sickn33) or simply ⭐ the repo.
**Antigravity Awesome Skills** is a curated, battle-tested library of **954+ high-performance agentic skills** designed to work seamlessly across all major AI coding assistants:
**Antigravity Awesome Skills** is a curated, battle-tested library of **968+ high-performance agentic skills** designed to work seamlessly across all major AI coding assistants:
- 🟣 **Claude Code** (Anthropic CLI)
- 🔵 **Gemini CLI** (Google DeepMind)
@@ -30,7 +30,7 @@ If this project helps you, you can [support it here](https://buymeacoffee.com/si
- ⚪ **OpenCode** (Open-source CLI)
- 🌸 **AdaL CLI** (Self-evolving Coding Agent)
This repository provides essential skills to transform your AI assistant into a **full-stack digital agency**, including official capabilities from **Anthropic**, **OpenAI**, **Google**, **Microsoft**, **Supabase**, and **Vercel Labs**.
This repository provides essential skills to transform your AI assistant into a **full-stack digital agency**, including official capabilities from **Anthropic**, **OpenAI**, **Google**, **Microsoft**, **Supabase**, **Apify**, and **Vercel Labs**.
## Table of Contents
@@ -42,7 +42,7 @@ This repository provides essential skills to transform your AI assistant into a
- [🎁 Curated Collections (Bundles)](#curated-collections)
- [🧭 Antigravity Workflows](#antigravity-workflows)
- [📦 Features & Categories](#features--categories)
- [📚 Browse 954+ Skills](#browse-954-skills)
- [📚 Browse 968+ Skills](#browse-968-skills)
- [🤝 How to Contribute](#how-to-contribute)
- [💬 Community](#community)
- [☕ Support the Project](#support-the-project)
@@ -55,7 +55,7 @@ This repository provides essential skills to transform your AI assistant into a
## New Here? Start Here!
**Welcome to the V6.5.0 Interactive Web Edition.** This isn't just a list of scripts; it's a complete operating system for your AI Agent.
**Welcome to the V6.7.0 Interactive Web Edition.** This isn't just a list of scripts; it's a complete operating system for your AI Agent.
### 1. 🐣 Context: What is this?
@@ -341,7 +341,7 @@ The repository is organized into specialized domains to transform your AI into a
Counts change as new skills are added. For the current full registry, see [CATALOG.md](CATALOG.md).
## Browse 954+ Skills
## Browse 968+ Skills
We have moved the full skill registry to a dedicated catalog to keep this README clean, and we've also introduced an interactive **Web App**!
@@ -472,6 +472,7 @@ This collection would not be possible without the incredible work of the Claude
- **[supabase/agent-skills](https://github.com/supabase/agent-skills)**: Supabase official skills - Postgres Best Practices.
- **[microsoft/skills](https://github.com/microsoft/skills)**: Official Microsoft skills - Azure cloud services, Bot Framework, Cognitive Services, and enterprise development patterns across .NET, Python, TypeScript, Go, Rust, and Java.
- **[google-gemini/gemini-skills](https://github.com/google-gemini/gemini-skills)**: Official Gemini skills - Gemini API, SDK and model interactions.
- **[apify/agent-skills](https://github.com/apify/agent-skills)**: Official Apify skills - Web scraping, data extraction and automation.
### Community Contributors
@@ -499,6 +500,8 @@ This collection would not be possible without the incredible work of the Claude
- **[nedcodes-ok/rule-porter](https://github.com/nedcodes-ok/rule-porter)**: Bidirectional rule converter between Cursor (.mdc), Claude Code (CLAUDE.md), GitHub Copilot, Windsurf, and legacy .cursorrules formats. Zero dependencies.
- **[SSOJet/skills](https://github.com/ssojet/skills)**: Production-ready SSOJet skills and integration guides for popular frameworks and platforms — Node.js, Next.js, React, Java, .NET Core, Go, iOS, Android, and more. Works seamlessly with SSOJet SAML, OIDC, and enterprise SSO flows. Works with Cursor, Antigravity, Claude Code, and Windsurf.
- **[MojoAuth/skills](https://github.com/MojoAuth/skills)**: Production-ready MojoAuth guides and examples for popular frameworks like Node.js, Next.js, React, Java, .NET Core, Go, iOS, and Android.
- **[Xquik-dev/x-twitter-scraper](https://github.com/Xquik-dev/x-twitter-scraper)**: X (Twitter) data platform — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction tools, MCP server.
- **[shmlkv/dna-claude-analysis](https://github.com/shmlkv/dna-claude-analysis)**: Personal genome analysis toolkit — Python scripts analyzing raw DNA data across 17 categories (health risks, ancestry, pharmacogenomics, nutrition, psychology, etc.) with terminal-style single-page HTML visualization.
### Inspirations
@@ -517,56 +520,75 @@ Made with [contrib.rocks](https://contrib.rocks).
We officially thank the following contributors for their help in making this repository awesome!
- [@sck000](https://github.com/sck000)
- [@munir-abbasi](https://github.com/munir-abbasi)
- [@sickn33](https://github.com/sickn33)
- [@munir-abbasi](https://github.com/munir-abbasi)
- [@ssumanbiswas](https://github.com/ssumanbiswas)
- [@zinzied](https://github.com/zinzied)
- [@Mohammad-Faiz-Cloud-Engineer](https://github.com/Mohammad-Faiz-Cloud-Engineer)
- [@Dokhacgiakhoa](https://github.com/Dokhacgiakhoa)
- [@IanJ332](https://github.com/IanJ332)
- [@chauey](https://github.com/chauey)
- [@PabloSMD](https://github.com/PabloSMD)
- [@GuppyTheCat](https://github.com/GuppyTheCat)
- [@Tiger-Foxx](https://github.com/Tiger-Foxx)
- [@arathiesh](https://github.com/arathiesh)
- [@liyin2015](https://github.com/liyin2015)
- [@1bcMax](https://github.com/1bcMax)
- [@ALEKGG1](https://github.com/ALEKGG1)
- [@ar27111994](https://github.com/ar27111994)
- [@BenedictKing](https://github.com/BenedictKing)
- [@whatiskadudoing](https://github.com/whatiskadudoing)
- [@LocNguyenSGU](https://github.com/LocNguyenSGU)
- [@yubing744](https://github.com/yubing744)
- [@8hrsk](https://github.com/8hrsk)
- [@itsmeares](https://github.com/itsmeares)
- [@GuppyTheCat](https://github.com/GuppyTheCat)
- [@fernandorych](https://github.com/fernandorych)
- [@nikolasdehor](https://github.com/nikolasdehor)
- [@talesperito](https://github.com/talesperito)
- [@jackjin1997](https://github.com/jackjin1997)
- [@HuynhNhatKhanh](https://github.com/HuynhNhatKhanh)
- [@liyin2015](https://github.com/liyin2015)
- [@arathiesh](https://github.com/arathiesh)
- [@Tiger-Foxx](https://github.com/Tiger-Foxx)
- [@Musayrlsms](https://github.com/Musayrlsms)
- [@sohamganatra](https://github.com/sohamganatra)
- [@SuperJMN](https://github.com/SuperJMN)
- [@SebConejo](https://github.com/SebConejo)
- [@Onsraa](https://github.com/Onsraa)
- [@truongnmt](https://github.com/truongnmt)
- [@code-vj](https://github.com/code-vj)
- [@viktor-ferenczi](https://github.com/viktor-ferenczi)
- [@vprudnikoff](https://github.com/vprudnikoff)
- [@Vonfry](https://github.com/Vonfry)
- [@Wittlesus](https://github.com/Wittlesus)
- [@avimak](https://github.com/avimak)
- [@buzzbysolcex](https://github.com/buzzbysolcex)
- [@c1c3ru](https://github.com/c1c3ru)
- [@ckdwns9121](https://github.com/ckdwns9121)
- [@developer-victor](https://github.com/developer-victor)
- [@fbientrigo](https://github.com/fbientrigo)
- [@junited31](https://github.com/junited31)
- [@KrisnaSantosa15](https://github.com/KrisnaSantosa15)
- [@nocodemf](https://github.com/nocodemf)
- [@sstklen](https://github.com/sstklen)
- [@taksrules](https://github.com/taksrules)
- [@thuanlm215](https://github.com/thuanlm215)
- [@zebbern](https://github.com/zebbern)
- [@vuth-dogo](https://github.com/vuth-dogo)
- [@mvanhorn](https://github.com/mvanhorn)
- [@rookie-ricardo](https://github.com/rookie-ricardo)
- [@evandro-miguel](https://github.com/evandro-miguel)
- [@raeef1001](https://github.com/raeef1001)
- [@devchangjun](https://github.com/devchangjun)
- [@jackjin1997](https://github.com/jackjin1997)
- [@ericgandrade](https://github.com/ericgandrade)
- [@sohamganatra](https://github.com/sohamganatra)
- [@Nguyen-Van-Chan](https://github.com/Nguyen-Van-Chan)
- [@8hrsk](https://github.com/8hrsk)
- [@Wittlesus](https://github.com/Wittlesus)
- [@Vonfry](https://github.com/Vonfry)
- [@ssumanbiswas](https://github.com/ssumanbiswas)
- [@amartelr](https://github.com/amartelr)
- [@fernandorych](https://github.com/fernandorych)
- [@GeekLuffy](https://github.com/GeekLuffy)
- [@zinzied](https://github.com/zinzied)
- [@code-vj](https://github.com/code-vj)
- [@thuanlm](https://github.com/thuanlm)
- [@ALEKGG1](https://github.com/ALEKGG1)
- [@Abdulrahmansoliman](https://github.com/Abdulrahmansoliman)
- [@alexmvie](https://github.com/alexmvie)
- [@Andruia](https://github.com/Andruia)
- [@acbhatt12](https://github.com/acbhatt12)
- [@BenedictKing](https://github.com/BenedictKing)
- [@rcigor](https://github.com/rcigor)
- [@whatiskadudoing](https://github.com/whatiskadudoing)
- [@k-kolomeitsev](https://github.com/k-kolomeitsev)
- [@Krishna-Modi12](https://github.com/Krishna-Modi12)
- [@kromahlusenii-ops](https://github.com/kromahlusenii-ops)
- [@djmahe4](https://github.com/djmahe4)
- [@maxdml](https://github.com/maxdml)
- [@mertbaskurt](https://github.com/mertbaskurt)
- [@nedcodes-ok](https://github.com/nedcodes-ok)
- [@LocNguyenSGU](https://github.com/LocNguyenSGU)
- [@KhaiTrang1995](https://github.com/KhaiTrang1995)
- [@sharmanilay](https://github.com/sharmanilay)
- [@yubing744](https://github.com/yubing744)
- [@PabloASMD](https://github.com/PabloASMD)
- [@0xrohitgarg](https://github.com/0xrohitgarg)
- [@Silverov](https://github.com/Silverov)
- [@shmlkv](https://github.com/shmlkv)
- [@kriptoburak](https://github.com/kriptoburak)
---

89
START_APP.bat
View File

@@ -14,101 +14,15 @@ IF %ERRORLEVEL% NEQ 0 (
exit /b 1
)
:: ===== Auto-Update Skills from GitHub =====
echo [INFO] Checking for skill updates...
:: Method 1: Try Git first (if available)
WHERE git >nul 2>nul
IF %ERRORLEVEL% EQU 0 goto :USE_GIT
:: Method 2: Try PowerShell download (fallback)
echo [INFO] Git not found. Using alternative download method...
goto :USE_POWERSHELL
:USE_GIT
:: Add upstream remote if not already set
git remote get-url upstream >nul 2>nul
IF %ERRORLEVEL% EQU 0 goto :DO_FETCH
echo [INFO] Adding upstream remote...
git remote add upstream https://github.com/sickn33/antigravity-awesome-skills.git
:DO_FETCH
echo [INFO] Fetching latest skills from original repo...
git fetch upstream >nul 2>nul
IF %ERRORLEVEL% NEQ 0 goto :FETCH_FAIL
goto :DO_MERGE
:FETCH_FAIL
echo [WARN] Could not fetch updates via Git. Trying alternative method...
goto :USE_POWERSHELL
:DO_MERGE
:: Surgically extract ONLY the /skills/ folder from upstream to avoid all merge conflicts
git checkout upstream/main -- skills >nul 2>nul
IF %ERRORLEVEL% NEQ 0 goto :MERGE_FAIL
:: Save the updated skills to local history silently
git commit -m "auto-update: sync latest skills from upstream" >nul 2>nul
echo [INFO] Skills updated successfully from original repo!
goto :SKIP_UPDATE
:MERGE_FAIL
echo [WARN] Could not update skills via Git. Trying alternative method...
goto :USE_POWERSHELL
:USE_POWERSHELL
echo [INFO] Downloading latest skills via HTTPS...
if exist "update_temp" rmdir /S /Q "update_temp" >nul 2>nul
if exist "update.zip" del "update.zip" >nul 2>nul
:: Download the latest repository as ZIP
powershell -Command "Invoke-WebRequest -Uri 'https://github.com/sickn33/antigravity-awesome-skills/archive/refs/heads/main.zip' -OutFile 'update.zip' -UseBasicParsing" >nul 2>nul
IF %ERRORLEVEL% NEQ 0 goto :DOWNLOAD_FAIL
:: Extract and update skills
echo [INFO] Extracting latest skills...
powershell -Command "Expand-Archive -Path 'update.zip' -DestinationPath 'update_temp' -Force" >nul 2>nul
IF %ERRORLEVEL% NEQ 0 goto :EXTRACT_FAIL
:: Copy only the skills folder
if exist "update_temp\antigravity-awesome-skills-main\skills" (
echo [INFO] Updating skills directory...
xcopy /E /Y /I "update_temp\antigravity-awesome-skills-main\skills" "skills" >nul 2>nul
echo [INFO] Skills updated successfully without Git!
) else (
echo [WARN] Could not find skills folder in downloaded archive.
goto :UPDATE_FAIL
)
:: Cleanup
del "update.zip" >nul 2>nul
rmdir /S /Q "update_temp" >nul 2>nul
goto :SKIP_UPDATE
:DOWNLOAD_FAIL
echo [WARN] Failed to download skills update (network issue or no internet).
goto :UPDATE_FAIL
:EXTRACT_FAIL
echo [WARN] Failed to extract downloaded skills archive.
goto :UPDATE_FAIL
:UPDATE_FAIL
echo [INFO] Continuing with local skills version...
echo [INFO] To manually update skills later, run: npm run update:skills
:SKIP_UPDATE
:: Check/Install dependencies
cd web-app
:CHECK_DEPS
if not exist "node_modules\" (
echo [INFO] Dependencies not found. Installing...
goto :INSTALL_DEPS
)
:: Verify dependencies aren't corrupted (e.g. esbuild arch mismatch after update)
:: Verify dependencies aren't corrupted
echo [INFO] Verifying app dependencies...
call npx -y vite --version >nul 2>nul
if %ERRORLEVEL% NEQ 0 (
@@ -138,6 +52,7 @@ call npm run app:setup
:: Start App
echo [INFO] Starting Web App...
echo [INFO] Opening default browser...
echo [INFO] Use the Sync Skills button in the app to update skills from GitHub!
cd web-app
call npx -y vite --open

BIN
assets/star-history.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 50 KiB

After

Width:  |  Height:  |  Size: 50 KiB

1
data/aliases.json
View File

@@ -7,6 +7,7 @@
"agent-orchestration-optimize": "agent-orchestration-multi-agent-optimize",
"android-jetpack-expert": "android-jetpack-compose-expert",
"api-testing-mock": "api-testing-observability-api-mock",
"apify-brand-monitoring": "apify-brand-reputation-monitoring",
"templates": "app-builder/templates",
"application-performance-optimization": "application-performance-performance-optimization",
"azure-ai-dotnet": "azure-ai-agents-persistent-dotnet",

103
data/bundles.json
View File

@@ -18,6 +18,7 @@
"api-security-best-practices",
"api-security-testing",
"api-testing-observability-api-mock",
"apify-actorization",
"app-store-optimization",
"appdeploy",
"application-performance-performance-optimization",
@@ -27,15 +28,21 @@
"azure-ai-agents-persistent-java",
"azure-ai-anomalydetector-java",
"azure-ai-contentsafety-java",
"azure-ai-contentsafety-py",
"azure-ai-contentunderstanding-py",
"azure-ai-formrecognizer-java",
"azure-ai-ml-py",
"azure-ai-projects-java",
"azure-ai-projects-py",
"azure-ai-projects-ts",
"azure-ai-transcription-py",
"azure-ai-translation-ts",
"azure-ai-vision-imageanalysis-java",
"azure-ai-voicelive-java",
"azure-ai-voicelive-py",
"azure-ai-voicelive-ts",
"azure-appconfiguration-java",
"azure-appconfiguration-py",
"azure-appconfiguration-ts",
"azure-communication-callautomation-java",
"azure-communication-callingserver-java",
@@ -43,34 +50,64 @@
"azure-communication-common-java",
"azure-communication-sms-java",
"azure-compute-batch-java",
"azure-containerregistry-py",
"azure-cosmos-db-py",
"azure-cosmos-java",
"azure-cosmos-py",
"azure-cosmos-rust",
"azure-cosmos-ts",
"azure-data-tables-java",
"azure-data-tables-py",
"azure-eventgrid-java",
"azure-eventgrid-py",
"azure-eventhub-java",
"azure-eventhub-py",
"azure-eventhub-rust",
"azure-eventhub-ts",
"azure-functions",
"azure-identity-java",
"azure-identity-py",
"azure-identity-rust",
"azure-identity-ts",
"azure-keyvault-certificates-rust",
"azure-keyvault-keys-rust",
"azure-keyvault-keys-ts",
"azure-keyvault-py",
"azure-keyvault-secrets-rust",
"azure-keyvault-secrets-ts",
"azure-messaging-webpubsub-java",
"azure-messaging-webpubsubservice-py",
"azure-mgmt-apicenter-dotnet",
"azure-mgmt-apicenter-py",
"azure-mgmt-apimanagement-dotnet",
"azure-mgmt-apimanagement-py",
"azure-mgmt-botservice-py",
"azure-mgmt-fabric-py",
"azure-monitor-ingestion-java",
"azure-monitor-ingestion-py",
"azure-monitor-opentelemetry-exporter-java",
"azure-monitor-opentelemetry-exporter-py",
"azure-monitor-opentelemetry-py",
"azure-monitor-opentelemetry-ts",
"azure-monitor-query-java",
"azure-monitor-query-py",
"azure-postgres-ts",
"azure-search-documents-py",
"azure-search-documents-ts",
"azure-security-keyvault-keys-java",
"azure-security-keyvault-secrets-java",
"azure-servicebus-py",
"azure-servicebus-ts",
"azure-speech-to-text-rest-py",
"azure-storage-blob-java",
"azure-storage-blob-py",
"azure-storage-blob-rust",
"azure-storage-blob-ts",
"azure-storage-file-datalake-py",
"azure-storage-file-share-py",
"azure-storage-file-share-ts",
"azure-storage-queue-py",
"azure-storage-queue-ts",
"azure-web-pubsub-ts",
"backend-architect",
"backend-dev-guidelines",
@@ -97,6 +134,7 @@
"documentation",
"documentation-generation-doc-generate",
"documentation-templates",
"dotnet-architect",
"dotnet-backend",
"dotnet-backend-patterns",
"exa-search",
@@ -132,6 +170,8 @@
"javascript-testing-patterns",
"javascript-typescript-typescript-scaffold",
"launch-strategy",
"m365-agents-py",
"m365-agents-ts",
"makepad-skills",
"manifest",
"memory-safety-patterns",
@@ -170,6 +210,7 @@
"react-patterns",
"react-state-management",
"react-ui-patterns",
"reference-builder",
"remotion-best-practices",
"ruby-pro",
"rust-async-patterns",
@@ -179,6 +220,7 @@
"senior-architect",
"senior-fullstack",
"shopify-apps",
"shopify-development",
"slack-automation",
"slack-bot-builder",
"stitch-ui-design",
@@ -217,6 +259,7 @@
"auth-implementation-patterns",
"aws-penetration-testing",
"azure-cosmos-db-py",
"azure-keyvault-py",
"azure-keyvault-secrets-rust",
"azure-keyvault-secrets-ts",
"azure-security-keyvault-keys-dotnet",
@@ -239,25 +282,34 @@
"ethical-hacking-methodology",
"find-bugs",
"firebase",
"firmware-analyst",
"framework-migration-deps-upgrade",
"frontend-mobile-security-xss-scan",
"frontend-security-coder",
"gdpr-data-handling",
"graphql-architect",
"k8s-manifest-generator",
"k8s-security-policies",
"laravel-expert",
"laravel-security-audit",
"legal-advisor",
"linkerd-patterns",
"loki-mode",
"m365-agents-dotnet",
"m365-agents-py",
"malware-analyst",
"mobile-security-coder",
"nestjs-expert",
"network-engineer",
"nextjs-supabase-auth",
"nodejs-best-practices",
"notebooklm",
"openapi-spec-generation",
"payment-integration",
"pci-compliance",
"pentest-checklist",
"plaid-fintech",
"quant-analyst",
"risk-manager",
"risk-metrics-calculation",
"sast-configuration",
@@ -282,6 +334,7 @@
"threat-mitigation-mapping",
"threat-modeling-expert",
"top-web-vulnerabilities",
"ui-visual-validator",
"varlock-claude-skill",
"vulnerability-scanner",
"web-design-guidelines",
@@ -294,8 +347,15 @@
"description": "Kubernetes and service mesh essentials.",
"skills": [
"azure-cosmos-db-py",
"azure-identity-dotnet",
"azure-identity-java",
"azure-identity-py",
"azure-identity-ts",
"azure-messaging-webpubsubservice-py",
"azure-mgmt-botservice-dotnet",
"azure-mgmt-botservice-py",
"azure-servicebus-dotnet",
"azure-servicebus-py",
"azure-servicebus-ts",
"chrome-extension-developer",
"cloud-devops",
@@ -308,6 +368,7 @@
"k8s-security-policies",
"kubernetes-architect",
"kubernetes-deployment",
"legal-advisor",
"linkerd-patterns",
"linux-troubleshooting",
"microservices-patterns",
@@ -325,21 +386,41 @@
"airflow-dag-patterns",
"analytics-tracking",
"angular-ui-patterns",
"apify-actor-development",
"apify-content-analytics",
"apify-ecommerce",
"apify-ultimate-scraper",
"appdeploy",
"azure-ai-document-intelligence-dotnet",
"azure-ai-document-intelligence-ts",
"azure-ai-textanalytics-py",
"azure-cosmos-db-py",
"azure-cosmos-java",
"azure-cosmos-py",
"azure-cosmos-rust",
"azure-cosmos-ts",
"azure-data-tables-java",
"azure-data-tables-py",
"azure-eventhub-java",
"azure-eventhub-rust",
"azure-eventhub-ts",
"azure-maps-search-dotnet",
"azure-monitor-ingestion-java",
"azure-monitor-ingestion-py",
"azure-monitor-query-java",
"azure-monitor-query-py",
"azure-postgres-ts",
"azure-resource-manager-mysql-dotnet",
"azure-resource-manager-postgresql-dotnet",
"azure-resource-manager-sql-dotnet",
"azure-security-keyvault-secrets-java",
"azure-storage-file-datalake-py",
"blockrun",
"business-analyst",
"cc-skill-backend-patterns",
"cc-skill-clickhouse-io",
"claude-d3js-skill",
"content-marketer",
"data-engineer",
"data-engineering-data-driven-feature",
"data-engineering-data-pipeline",
@@ -365,7 +446,9 @@
"google-analytics-automation",
"googlesheets-automation",
"graphql",
"ios-developer",
"kpi-dashboard-design",
"legal-advisor",
"libreoffice/base",
"libreoffice/calc",
"loki-mode",
@@ -376,13 +459,18 @@
"nextjs-best-practices",
"nodejs-backend-patterns",
"pci-compliance",
"php-pro",
"postgres-best-practices",
"postgresql",
"postgresql-optimization",
"prisma-expert",
"programmatic-seo",
"pydantic-models-py",
"quant-analyst",
"rag-implementation",
"react-ui-patterns",
"scala-pro",
"schema-markup",
"segment-cdp",
"sendgrid-automation",
"senior-architect",
@@ -395,6 +483,7 @@
"unity-ecs-patterns",
"using-neon",
"vector-database-engineer",
"x-twitter-scraper",
"xlsx-official",
"youtube-automation"
]
@@ -405,10 +494,14 @@
"agent-evaluation",
"airflow-dag-patterns",
"api-testing-observability-api-mock",
"apify-brand-reputation-monitoring",
"application-performance-performance-optimization",
"aws-serverless",
"azd-deployment",
"azure-ai-anomalydetector-java",
"azure-mgmt-applicationinsights-dotnet",
"azure-mgmt-arizeaiobservabilityeval-dotnet",
"azure-mgmt-weightsandbiases-dotnet",
"azure-microsoft-playwright-testing-ts",
"azure-monitor-opentelemetry-ts",
"backend-development-feature-development",
@@ -425,6 +518,7 @@
"devops-troubleshooter",
"distributed-debugging-debug-trace",
"distributed-tracing",
"django-pro",
"docker-expert",
"e2e-testing-patterns",
"error-debugging-error-analysis",
@@ -432,6 +526,7 @@
"error-diagnostics-error-analysis",
"error-diagnostics-error-trace",
"expo-deployment",
"flutter-expert",
"game-development/game-art",
"git-pr-workflows-git-workflow",
"gitlab-ci-patterns",
@@ -443,12 +538,15 @@
"incident-response-smart-fix",
"incident-runbook-templates",
"kpi-dashboard-design",
"kubernetes-architect",
"kubernetes-deployment",
"langfuse",
"llm-app-patterns",
"loki-mode",
"machine-learning-ops-ml-pipeline",
"malware-analyst",
"manifest",
"ml-engineer",
"ml-pipeline-workflow",
"observability-engineer",
"observability-monitoring-monitor-setup",
@@ -464,8 +562,11 @@
"service-mesh-expert",
"service-mesh-observability",
"slo-implementation",
"temporal-python-pro",
"unity-developer",
"vercel-deploy-claimable",
"vercel-deployment"
"vercel-deployment",
"x-twitter-scraper"
]
}
},

3373
data/catalog.json
View File

File diff suppressed because it is too large Load Diff

20
docs/SOURCES.md
View File

@@ -3,16 +3,16 @@
We believe in giving credit where credit is due.
If you recognize your work here and it is not properly attributed, please open an Issue.
| Skill / Category | Original Source | License | Notes |
| :-------------------------- | :----------------------------------------------------------------- | :------------- | :---------------------------- |
| `cloud-penetration-testing` | [HackTricks](https://book.hacktricks.xyz/) | MIT / CC-BY-SA | Adapted for agentic use. |
| `active-directory-attacks` | [HackTricks](https://book.hacktricks.xyz/) | MIT / CC-BY-SA | Adapted for agentic use. |
| `owasp-top-10` | [OWASP](https://owasp.org/) | CC-BY-SA | Methodology adapted. |
| `burp-suite-testing` | [PortSwigger](https://portswigger.net/burp) | N/A | Usage guide only (no binary). |
| `crewai` | [CrewAI](https://github.com/joaomdmoura/crewAI) | MIT | Framework guides. |
| `langgraph` | [LangGraph](https://github.com/langchain-ai/langgraph) | MIT | Framework guides. |
| `react-patterns` | [React Docs](https://react.dev/) | CC-BY | Official patterns. |
| **All Official Skills** | [Anthropic / Google / OpenAI / Microsoft / Supabase / Vercel Labs] | Proprietary | Usage encouraged by vendors. |
| Skill / Category | Original Source | License | Notes |
| :-------------------------- | :------------------------------------------------------------------------- | :------------- | :---------------------------- |
| `cloud-penetration-testing` | [HackTricks](https://book.hacktricks.xyz/) | MIT / CC-BY-SA | Adapted for agentic use. |
| `active-directory-attacks` | [HackTricks](https://book.hacktricks.xyz/) | MIT / CC-BY-SA | Adapted for agentic use. |
| `owasp-top-10` | [OWASP](https://owasp.org/) | CC-BY-SA | Methodology adapted. |
| `burp-suite-testing` | [PortSwigger](https://portswigger.net/burp) | N/A | Usage guide only (no binary). |
| `crewai` | [CrewAI](https://github.com/joaomdmoura/crewAI) | MIT | Framework guides. |
| `langgraph` | [LangGraph](https://github.com/langchain-ai/langgraph) | MIT | Framework guides. |
| `react-patterns` | [React Docs](https://react.dev/) | CC-BY | Official patterns. |
| **All Official Skills** | [Anthropic / Google / OpenAI / Microsoft / Supabase / Apify / Vercel Labs] | Proprietary | Usage encouraged by vendors. |
## Skills from VoltAgent/awesome-agent-skills

25
docs/vietnamese/README.vi.md
View File

@@ -30,7 +30,7 @@
Các trợ lý AI (như Claude Code, Cursor, hoặc Gemini) rất thông minh, nhưng chúng thiếu các **công cụ chuyên biệt**. Chúng không biết "Quy trình Triển khai" của công ty bạn hoặc cú pháp cụ thể cho "AWS CloudFormation".
**Skills** là các tệp markdown nhỏ dạy cho chúng cách thực hiện những tác vụ cụ thể này một cách chính xác trong mọi lần thực thi.
...
Repository này cung cấp các kỹ năng thiết yếu để biến trợ lý AI của bạn thành một **đội ngũ chuyên gia số toàn năng**, bao gồm các khả năng chính thức từ **Anthropic**, **OpenAI**, **Google**, **Supabase**, và **Vercel Labs**.
Repository này cung cấp các kỹ năng thiết yếu để biến trợ lý AI của bạn thành một **đội ngũ chuyên gia số toàn năng**, bao gồm các khả năng chính thức từ **Anthropic**, **OpenAI**, **Google**, **Supabase**, **Apify**, và **Vercel Labs**.
...
Cho dù bạn đang sử dụng **Gemini CLI**, **Claude Code**, **Codex CLI**, **Cursor**, **GitHub Copilot**, **Antigravity**, hay **OpenCode**, những kỹ năng này được thiết kế để có thể sử dụng ngay lập tức và tăng cường sức mạnh cho trợ lý AI của bạn.
@@ -40,17 +40,17 @@ Repository này tập hợp những khả năng tốt nhất từ khắp cộng
Repository được tổ chức thành các lĩnh vực chuyên biệt để biến AI của bạn thành một chuyên gia trên toàn bộ vòng đời phát triển phần mềm:
| Danh mục | Trọng tâm | Ví dụ kỹ năng |
| :--- | :--- | :--- |
| Kiến trúc (52) | Thiết kế hệ thống, ADRs, C4 và các mẫu có thể mở rộng | `architecture`, `c4-context`, `senior-architect` |
| Kinh doanh (35) | Tăng trưởng, định giá, CRO, SEO và thâm nhập thị trường | `copywriting`, `pricing-strategy`, `seo-audit` |
| Dữ liệu & AI (81) | Ứng dụng LLM, RAG, agents, khả năng quan sát, phân tích | `rag-engineer`, `prompt-engineer`, `langgraph` |
| Phát triển (72) | Làm chủ ngôn ngữ, mẫu thiết kế framework, chất lượng code | `typescript-expert`, `python-patterns`, `react-patterns` |
| Tổng quát (95) | Lập kế hoạch, tài liệu, vận hành sản phẩm, viết bài, hướng dẫn | `brainstorming`, `doc-coauthoring`, `writing-plans` |
| Hạ tầng (72) | DevOps, cloud, serverless, triển khai, CI/CD | `docker-expert`, `aws-serverless`, `vercel-deployment` |
| Bảo mật (107) | AppSec, pentesting, phân tích lỗ hổng, tuân thủ | `api-security-best-practices`, `sql-injection-testing`, `vulnerability-scanner` |
| Kiểm thử (21) | TDD, thiết kế kiểm thử, sửa lỗi, quy trình QA | `test-driven-development`, `testing-patterns`, `test-fixing` |
| Quy trình (17) | Tự động hóa, điều phối, công việc, agents | `workflow-automation`, `inngest`, `trigger-dev` |
| Danh mục | Trọng tâm | Ví dụ kỹ năng |
| :---------------- | :------------------------------------------------------------- | :------------------------------------------------------------------------------ |
| Kiến trúc (52) | Thiết kế hệ thống, ADRs, C4 và các mẫu có thể mở rộng | `architecture`, `c4-context`, `senior-architect` |
| Kinh doanh (35) | Tăng trưởng, định giá, CRO, SEO và thâm nhập thị trường | `copywriting`, `pricing-strategy`, `seo-audit` |
| Dữ liệu & AI (81) | Ứng dụng LLM, RAG, agents, khả năng quan sát, phân tích | `rag-engineer`, `prompt-engineer`, `langgraph` |
| Phát triển (72) | Làm chủ ngôn ngữ, mẫu thiết kế framework, chất lượng code | `typescript-expert`, `python-patterns`, `react-patterns` |
| Tổng quát (95) | Lập kế hoạch, tài liệu, vận hành sản phẩm, viết bài, hướng dẫn | `brainstorming`, `doc-coauthoring`, `writing-plans` |
| Hạ tầng (72) | DevOps, cloud, serverless, triển khai, CI/CD | `docker-expert`, `aws-serverless`, `vercel-deployment` |
| Bảo mật (107) | AppSec, pentesting, phân tích lỗ hổng, tuân thủ | `api-security-best-practices`, `sql-injection-testing`, `vulnerability-scanner` |
| Kiểm thử (21) | TDD, thiết kế kiểm thử, sửa lỗi, quy trình QA | `test-driven-development`, `testing-patterns`, `test-fixing` |
| Quy trình (17) | Tự động hóa, điều phối, công việc, agents | `workflow-automation`, `inngest`, `trigger-dev` |
## Bộ sưu tập Tuyển chọn
@@ -119,6 +119,7 @@ Bộ sưu tập này sẽ không thể hình thành nếu không có công việ
- **[vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills)**: Skills chính thức của Vercel Labs - Thực hành tốt nhất cho React, Hướng dẫn thiết kế Web.
- **[openai/skills](https://github.com/openai/skills)**: Danh mục skill của OpenAI Codex - Các kỹ năng của Agent, Trình tạo Skill, Lập kế hoạch Súc tích.
- **[supabase/agent-skills](https://github.com/supabase/agent-skills)**: Skills chính thức của Supabase - Thực hành tốt nhất cho Postgres.
- **[apify/agent-skills](https://github.com/apify/agent-skills)**: Skills chính thức của Apify - Web scraping, data extraction and automation.
### Những người đóng góp từ Cộng đồng

18
package.json
View File

@@ -1,20 +1,22 @@
{
"name": "antigravity-awesome-skills",
"version": "6.6.0",
"version": "6.7.0",
"description": "900+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.",
"license": "MIT",
"scripts": {
"validate": "python3 scripts/validate_skills.py",
"validate:strict": "python3 scripts/validate_skills.py --strict",
"index": "python3 scripts/generate_index.py",
"readme": "python3 scripts/update_readme.py",
"validate": "node scripts/run-python.js scripts/validate_skills.py",
"validate:strict": "node scripts/run-python.js scripts/validate_skills.py --strict",
"index": "node scripts/run-python.js scripts/generate_index.py",
"readme": "node scripts/run-python.js scripts/update_readme.py",
"chain": "npm run validate && npm run index && npm run readme",
"catalog": "node scripts/build-catalog.js",
"build": "npm run chain && npm run catalog",
"test": "node scripts/tests/validate_skills_headings.test.js && python3 scripts/tests/test_validate_skills_headings.py && python3 scripts/tests/inspect_microsoft_repo.py && python3 scripts/tests/test_comprehensive_coverage.py",
"sync:microsoft": "python3 scripts/sync_microsoft_skills.py",
"test": "node scripts/tests/run-test-suite.js",
"test:local": "node scripts/tests/run-test-suite.js --local",
"test:network": "node scripts/tests/run-test-suite.js --network",
"sync:microsoft": "node scripts/run-python.js scripts/sync_microsoft_skills.py",
"sync:all-official": "npm run sync:microsoft && npm run chain",
"update:skills": "python3 scripts/generate_index.py && copy skills_index.json web-app/public/skills.json",
"update:skills": "node scripts/run-python.js scripts/generate_index.py && node scripts/copy-file.js skills_index.json web-app/public/skills.json",
"app:setup": "node scripts/setup_web.js",
"app:install": "cd web-app && npm install",
"app:dev": "npm run app:setup && cd web-app && npm run dev",

14
release_notes.md Normal file
View File

@@ -0,0 +1,14 @@
## v6.2.0 - Interactive Web App & AWS IaC
**Feature release: Interactive Skills Web App, AWS Infrastructure as Code skills, and Chrome Extension / Cloudflare Workers developer skills.**
- **New skills** (PR #124): `cdk-patterns`, `cloudformation-best-practices`, `terraform-aws-modules`.
- **New skills** (PR #128): `chrome-extension-developer`, `cloudflare-workers-expert`.
- **Interactive Skills Web App** (PR #126): Local skills browser with `START_APP.bat`, setup, and `web-app/` project.
- **Shopify Development Skill Fix** (PR #125): Markdown syntax cleanup for `skills/shopify-development/SKILL.md`.
- **Community Sources** (PR #127): Added SSOJet skills and integration guides to Credits & Sources.
- **Registry**: Now tracking 930 skills.
---
_Upgrade: `git pull origin main` or `npx antigravity-awesome-skills`_

1
requirements.txt Normal file
View File

@@ -0,0 +1 @@
pyyaml>=6.0

48
scripts/auto_categorize_skills.py
View File

@@ -128,8 +128,10 @@ def categorize_skill(skill_name, description):
return None
import yaml
def auto_categorize(skills_dir, dry_run=False):
"""Auto-categorize skills and update generate_index.py"""
"""Auto-categorize skills and update SKILL.md files"""
skills = []
categorized_count = 0
already_categorized = 0
@@ -146,17 +148,19 @@ def auto_categorize(skills_dir, dry_run=False):
with open(skill_path, 'r', encoding='utf-8') as f:
content = f.read()
# Extract name and description from frontmatter
# Extract frontmatter and body
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
if not fm_match:
continue
fm_text = fm_match.group(1)
metadata = {}
for line in fm_text.split('\n'):
if ':' in line and not line.strip().startswith('#'):
key, val = line.split(':', 1)
metadata[key.strip()] = val.strip().strip('"').strip("'")
body = content[fm_match.end():]
try:
metadata = yaml.safe_load(fm_text) or {}
except yaml.YAMLError as e:
print(f"⚠️ {skill_id}: YAML error - {e}")
continue
skill_name = metadata.get('name', skill_id)
description = metadata.get('description', '')
@@ -186,32 +190,12 @@ def auto_categorize(skills_dir, dry_run=False):
})
if not dry_run:
# Update the SKILL.md file - add or replace category
fm_start = content.find('---')
fm_end = content.find('---', fm_start + 3)
metadata['category'] = new_category
new_fm = yaml.dump(metadata, sort_keys=False, allow_unicode=True, width=1000).strip()
new_content = f"---\n{new_fm}\n---" + body
if fm_start >= 0 and fm_end > fm_start:
frontmatter = content[fm_start:fm_end+3]
body = content[fm_end+3:]
# Check if category exists in frontmatter
if 'category:' in frontmatter:
# Replace existing category
new_frontmatter = re.sub(
r'category:\s*\w+',
f'category: {new_category}',
frontmatter
)
else:
# Add category before the closing ---
new_frontmatter = frontmatter.replace(
'\n---',
f'\ncategory: {new_category}\n---'
)
new_content = new_frontmatter + body
with open(skill_path, 'w', encoding='utf-8') as f:
f.write(new_content)
with open(skill_path, 'w', encoding='utf-8') as f:
f.write(new_content)
categorized_count += 1
else:

3
scripts/build-catalog.js
View File

@@ -628,7 +628,8 @@ function buildCatalog() {
category,
tags,
triggers,
path: path.relative(ROOT, skill.path),
// Normalize separators for deterministic cross-platform output.
path: path.relative(ROOT, skill.path).split(path.sep).join("/"),
});
}

71
scripts/copy-file.js Normal file
View File

@@ -0,0 +1,71 @@
#!/usr/bin/env node
'use strict';
const fs = require('node:fs');
const path = require('node:path');
const args = process.argv.slice(2);
if (args.length !== 2) {
console.error('Usage: node scripts/copy-file.js <source> <destination>');
process.exit(1);
}
const [sourceInput, destinationInput] = args;
const projectRoot = path.resolve(__dirname, '..');
const sourcePath = path.resolve(projectRoot, sourceInput);
const destinationPath = path.resolve(projectRoot, destinationInput);
const destinationDir = path.dirname(destinationPath);
function fail(message) {
console.error(message);
process.exit(1);
}
function isInsideProjectRoot(targetPath) {
const relativePath = path.relative(projectRoot, targetPath);
return relativePath === '' || (!relativePath.startsWith('..') && !path.isAbsolute(relativePath));
}
if (!isInsideProjectRoot(sourcePath) || !isInsideProjectRoot(destinationPath)) {
fail('Source and destination must resolve inside the project root.');
}
if (sourcePath === destinationPath) {
fail('Source and destination must be different files.');
}
if (!fs.existsSync(sourcePath)) {
fail(`Source file not found: ${sourceInput}`);
}
let sourceStats;
try {
sourceStats = fs.statSync(sourcePath);
} catch (error) {
fail(`Unable to read source file "${sourceInput}": ${error.message}`);
}
if (!sourceStats.isFile()) {
fail(`Source is not a file: ${sourceInput}`);
}
let destinationDirStats;
try {
destinationDirStats = fs.statSync(destinationDir);
} catch {
fail(`Destination directory not found: ${path.relative(projectRoot, destinationDir)}`);
}
if (!destinationDirStats.isDirectory()) {
fail(`Destination parent is not a directory: ${path.relative(projectRoot, destinationDir)}`);
}
try {
fs.copyFileSync(sourcePath, destinationPath);
} catch (error) {
fail(`Copy failed (${sourceInput} -> ${destinationInput}): ${error.message}`);
}
console.log(`Copied ${sourceInput} -> ${destinationInput}`);

43
scripts/fix_skills_metadata.py
View File

@@ -1,5 +1,6 @@
import os
import re
import yaml
def fix_skills(skills_dir):
for root, dirs, files in os.walk(skills_dir):
@@ -14,33 +15,31 @@ def fix_skills(skills_dir):
continue
fm_text = fm_match.group(1)
body = content[fm_match.end():]
folder_name = os.path.basename(root)
new_fm_lines = []
try:
metadata = yaml.safe_load(fm_text) or {}
except yaml.YAMLError as e:
print(f"⚠️ {skill_path}: YAML error - {e}")
continue
changed = False
for line in fm_text.split('\n'):
if line.startswith('name:'):
old_name = line.split(':', 1)[1].strip().strip('"').strip("'")
if old_name != folder_name:
new_fm_lines.append(f"name: {folder_name}")
changed = True
else:
new_fm_lines.append(line)
elif line.startswith('description:'):
desc = line.split(':', 1)[1].strip().strip('"').strip("'")
if len(desc) > 200:
# trim to 197 chars and add "..."
short_desc = desc[:197] + "..."
new_fm_lines.append(f'description: "{short_desc}"')
changed = True
else:
new_fm_lines.append(line)
else:
new_fm_lines.append(line)
# 1. Fix Name
if metadata.get('name') != folder_name:
metadata['name'] = folder_name
changed = True
# 2. Fix Description length
desc = metadata.get('description', '')
if isinstance(desc, str) and len(desc) > 200:
metadata['description'] = desc[:197] + "..."
changed = True
if changed:
new_fm_text = '\n'.join(new_fm_lines)
new_content = content[:fm_match.start(1)] + new_fm_text + content[fm_match.end(1):]
new_fm = yaml.dump(metadata, sort_keys=False, allow_unicode=True, width=1000).strip()
new_content = f"---\n{new_fm}\n---" + body
with open(skill_path, 'w', encoding='utf-8') as f:
f.write(new_content)
print(f"Fixed {skill_path}")

52
scripts/fix_yaml_quotes.py
View File

@@ -1,9 +1,9 @@
import os
import re
import json
import yaml
def fix_yaml_quotes(skills_dir):
print(f"Scanning for YAML quoting errors in {skills_dir}...")
print(f"Normalizing YAML frontmatter in {skills_dir}...")
fixed_count = 0
for root, dirs, files in os.walk(skills_dir):
@@ -21,42 +21,24 @@ def fix_yaml_quotes(skills_dir):
continue
fm_text = fm_match.group(1)
new_fm_lines = []
changed = False
body = content[fm_match.end():]
for line in fm_text.split('\n'):
if line.startswith('description:'):
key, val = line.split(':', 1)
val = val.strip()
# Store original to check if it matches the fixed version
orig_val = val
# Strip matching outer quotes if they exist
if val.startswith('"') and val.endswith('"') and len(val) >= 2:
val = val[1:-1]
elif val.startswith("'") and val.endswith("'") and len(val) >= 2:
val = val[1:-1]
# Now safely encode using JSON to handle internal escapes
safe_val = json.dumps(val)
if safe_val != orig_val:
new_line = f"description: {safe_val}"
new_fm_lines.append(new_line)
changed = True
continue
new_fm_lines.append(line)
try:
# safe_load and then dump will normalize quoting automatically
metadata = yaml.safe_load(fm_text) or {}
new_fm = yaml.dump(metadata, sort_keys=False, allow_unicode=True, width=1000).strip()
if changed:
new_fm_text = '\n'.join(new_fm_lines)
new_content = content[:fm_match.start(1)] + new_fm_text + content[fm_match.end(1):]
with open(file_path, 'w', encoding='utf-8') as f:
f.write(new_content)
print(f"Fixed quotes in {os.path.relpath(file_path, skills_dir)}")
fixed_count += 1
# Check if it actually changed something significant (beyond just style)
# but normalization is good anyway. We'll just compare the fm_text.
if new_fm.strip() != fm_text.strip():
new_content = f"---\n{new_fm}\n---" + body
with open(file_path, 'w', encoding='utf-8') as f:
f.write(new_content)
fixed_count += 1
except yaml.YAMLError as e:
print(f"⚠️ {file_path}: YAML error - {e}")
print(f"Total files fixed: {fixed_count}")
print(f"Total files normalized: {fixed_count}")
if __name__ == '__main__':
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))

6
scripts/generate_index.py
View File

@@ -59,9 +59,11 @@ def generate_index(skills_dir, output_file):
parent_dir = os.path.basename(os.path.dirname(root))
# Default values
rel_path = os.path.relpath(root, os.path.dirname(skills_dir))
# Force forward slashes for cross-platform JSON compatibility
skill_info = {
"id": dir_name,
"path": os.path.relpath(root, os.path.dirname(skills_dir)),
"path": rel_path.replace(os.sep, '/'),
"category": parent_dir if parent_dir != "skills" else None, # Will be overridden by frontmatter if present
"name": dir_name.replace("-", " ").title(),
"description": "",
@@ -117,7 +119,7 @@ def generate_index(skills_dir, output_file):
# Sort validation: by name
skills.sort(key=lambda x: (x["name"].lower(), x["id"].lower()))
with open(output_file, 'w', encoding='utf-8') as f:
with open(output_file, 'w', encoding='utf-8', newline='\n') as f:
json.dump(skills, f, indent=2)
print(f"✅ Generated rich index with {len(skills)} skills at: {output_file}")

15
scripts/generate_skills_report.py
View File

@@ -18,20 +18,19 @@ def get_project_root():
"""Get the project root directory."""
return os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
import yaml
def parse_frontmatter(content):
"""Parse frontmatter from SKILL.md content."""
"""Parse frontmatter from SKILL.md content using PyYAML."""
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
if not fm_match:
return None
fm_text = fm_match.group(1)
metadata = {}
for line in fm_text.split('\n'):
if ':' in line and not line.strip().startswith('#'):
key, val = line.split(':', 1)
metadata[key.strip()] = val.strip().strip('"').strip("'")
return metadata
try:
return yaml.safe_load(fm_text) or {}
except yaml.YAMLError:
return None
def generate_skills_report(output_file=None, sort_by='date'):
"""Generate a report of all skills with their metadata."""

48
scripts/manage_skill_dates.py
View File

@@ -26,45 +26,39 @@ def get_project_root():
"""Get the project root directory."""
return os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
import yaml
def parse_frontmatter(content):
"""Parse frontmatter from SKILL.md content."""
"""Parse frontmatter from SKILL.md content using PyYAML."""
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
if not fm_match:
return None, content
fm_text = fm_match.group(1)
metadata = {}
for line in fm_text.split('\n'):
if ':' in line and not line.strip().startswith('#'):
key, val = line.split(':', 1)
metadata[key.strip()] = val.strip().strip('"').strip("'")
return metadata, content
try:
metadata = yaml.safe_load(fm_text) or {}
return metadata, content
except yaml.YAMLError as e:
print(f"⚠️ YAML parsing error: {e}")
return None, content
def reconstruct_frontmatter(metadata):
"""Reconstruct frontmatter from metadata dict."""
lines = ["---"]
# Order: id, name, description, category, risk, source, tags, date_added
priority_keys = ['id', 'name', 'description', 'category', 'risk', 'source', 'tags']
"""Reconstruct frontmatter from metadata dict using PyYAML."""
# Ensure important keys are at the top if they exist
ordered = {}
priority_keys = ['id', 'name', 'description', 'category', 'risk', 'source', 'tags', 'date_added']
for key in priority_keys:
if key in metadata:
val = metadata[key]
if isinstance(val, list):
# Handle list fields like tags
lines.append(f'{key}: {val}')
elif ' ' in str(val) or any(c in str(val) for c in ':#"'):
lines.append(f'{key}: "{val}"')
else:
lines.append(f'{key}: {val}')
ordered[key] = metadata[key]
# Add date_added at the end
if 'date_added' in metadata:
lines.append(f'date_added: "{metadata["date_added"]}"')
lines.append("---")
return '\n'.join(lines)
# Add any remaining keys
for key, value in metadata.items():
if key not in ordered:
ordered[key] = value
fm_text = yaml.dump(ordered, sort_keys=False, allow_unicode=True, width=1000).strip()
return f"---\n{fm_text}\n---"
def update_skill_frontmatter(skill_path, metadata):
"""Update a skill's frontmatter with new metadata."""

6
scripts/normalize-frontmatter.js
View File

@@ -14,6 +14,9 @@ const ALLOWED_FIELDS = new Set([
'compatibility',
'metadata',
'allowed-tools',
'date_added',
'category',
'id',
]);
function isPlainObject(value) {
@@ -122,7 +125,8 @@ function normalizeSkill(skillId) {
if (!modified) return false;
const ordered = {};
for (const key of ['name', 'description', 'license', 'compatibility', 'allowed-tools', 'metadata']) {
const order = ['id', 'name', 'description', 'category', 'risk', 'source', 'license', 'compatibility', 'date_added', 'allowed-tools', 'metadata'];
for (const key of order) {
if (updated[key] !== undefined) {
ordered[key] = updated[key];
}

90
scripts/run-python.js Normal file
View File

@@ -0,0 +1,90 @@
#!/usr/bin/env node
'use strict';
const { spawn, spawnSync } = require('node:child_process');
const args = process.argv.slice(2);
if (args.length === 0) {
console.error('Usage: node scripts/run-python.js <script.py> [args...]');
process.exit(1);
}
function uniqueCandidates(candidates) {
const seen = new Set();
const unique = [];
for (const candidate of candidates) {
const key = candidate.join('\u0000');
if (!seen.has(key)) {
seen.add(key);
unique.push(candidate);
}
}
return unique;
}
function getPythonCandidates() {
// Optional override for CI/local pinning without editing scripts.
const configuredPython =
process.env.ANTIGRAVITY_PYTHON || process.env.npm_config_python;
const candidates = [
configuredPython ? [configuredPython] : null,
// Keep this ordered list easy to update if project requirements change.
['python3'],
['python'],
['py', '-3'],
].filter(Boolean);
return uniqueCandidates(candidates);
}
function canRun(candidate) {
const [command, ...baseArgs] = candidate;
const probe = spawnSync(
command,
[...baseArgs, '-c', 'import sys; raise SystemExit(0 if sys.version_info[0] == 3 else 1)'],
{
stdio: 'ignore',
shell: false,
},
);
return probe.error == null && probe.status === 0;
}
const pythonCandidates = getPythonCandidates();
const selected = pythonCandidates.find(canRun);
if (!selected) {
console.error(
'Unable to find a Python 3 interpreter. Tried: python3, python, py -3',
);
process.exit(1);
}
const [command, ...baseArgs] = selected;
const child = spawn(command, [...baseArgs, ...args], {
stdio: 'inherit',
shell: false,
});
child.on('error', (error) => {
console.error(`Failed to start Python interpreter "${command}": ${error.message}`);
process.exit(1);
});
child.on('exit', (code, signal) => {
if (signal) {
try {
process.kill(process.pid, signal);
} catch {
process.exit(1);
}
return;
}
process.exit(code ?? 1);
});

16
scripts/sync_microsoft_skills.py
View File

@@ -59,8 +59,10 @@ def cleanup_previous_sync():
return removed_count
import yaml
def extract_skill_name(skill_md_path: Path) -> str | None:
"""Extract the 'name' field from SKILL.md YAML frontmatter."""
"""Extract the 'name' field from SKILL.md YAML frontmatter using PyYAML."""
try:
content = skill_md_path.read_text(encoding="utf-8")
except Exception:
@@ -70,13 +72,11 @@ def extract_skill_name(skill_md_path: Path) -> str | None:
if not fm_match:
return None
for line in fm_match.group(1).splitlines():
match = re.match(r"^name:\s*(.+)$", line)
if match:
value = match.group(1).strip().strip("\"'")
if value:
return value
return None
try:
data = yaml.safe_load(fm_match.group(1)) or {}
return data.get('name')
except Exception:
return None
def generate_fallback_name(relative_path: Path) -> str:

86
scripts/tests/inspect_microsoft_repo.py
View File

@@ -5,13 +5,61 @@ Shows the repository layout, skill locations, and what flat names would be gener
"""
import re
import io
import shutil
import subprocess
import sys
import tempfile
import traceback
import uuid
from pathlib import Path
MS_REPO = "https://github.com/microsoft/skills.git"
def create_clone_target(prefix: str) -> Path:
"""Return a writable, non-existent path for git clone destination."""
repo_tmp_root = Path(__file__).resolve().parents[2] / ".tmp" / "tests"
candidate_roots = (repo_tmp_root, Path(tempfile.gettempdir()))
last_error: OSError | None = None
for root in candidate_roots:
try:
root.mkdir(parents=True, exist_ok=True)
probe_file = root / f".{prefix}write-probe-{uuid.uuid4().hex}.tmp"
with probe_file.open("xb"):
pass
probe_file.unlink()
return root / f"{prefix}{uuid.uuid4().hex}"
except OSError as exc:
last_error = exc
if last_error is not None:
raise last_error
raise OSError("Unable to determine clone destination")
def configure_utf8_output() -> None:
"""Best-effort UTF-8 stdout/stderr on Windows without dropping diagnostics."""
for stream_name in ("stdout", "stderr"):
stream = getattr(sys, stream_name)
try:
stream.reconfigure(encoding="utf-8", errors="backslashreplace")
continue
except Exception:
pass
buffer = getattr(stream, "buffer", None)
if buffer is not None:
setattr(
sys,
stream_name,
io.TextIOWrapper(
buffer, encoding="utf-8", errors="backslashreplace"
),
)
def extract_skill_name(skill_md_path: Path) -> str | None:
"""Extract the 'name' field from SKILL.md YAML frontmatter."""
try:
@@ -37,18 +85,26 @@ def inspect_repo():
print("🔍 Inspecting Microsoft Skills Repository Structure")
print("=" * 60)
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
repo_path: Path | None = None
try:
repo_path = create_clone_target(prefix="ms-skills-")
print("\n1️⃣ Cloning repository...")
subprocess.run(
["git", "clone", "--depth", "1", MS_REPO, str(temp_path)],
check=True,
capture_output=True,
)
try:
subprocess.run(
["git", "clone", "--depth", "1", MS_REPO, str(repo_path)],
check=True,
capture_output=True,
text=True,
)
except subprocess.CalledProcessError as exc:
print("\n❌ git clone failed.", file=sys.stderr)
if exc.stderr:
print(exc.stderr.strip(), file=sys.stderr)
raise
# Find all SKILL.md files
all_skill_mds = list(temp_path.rglob("SKILL.md"))
all_skill_mds = list(repo_path.rglob("SKILL.md"))
print(f"\n2️⃣ Total SKILL.md files found: {len(all_skill_mds)}")
# Show flat name mapping
@@ -59,7 +115,7 @@ def inspect_repo():
for skill_md in sorted(all_skill_mds, key=lambda p: str(p)):
try:
rel = skill_md.parent.relative_to(temp_path)
rel = skill_md.parent.relative_to(repo_path)
except ValueError:
rel = skill_md.parent
@@ -87,12 +143,18 @@ def inspect_repo():
f"\n4️⃣ ✅ No name collisions — all {len(names_seen)} names are unique!")
print("\n✨ Inspection complete!")
finally:
if repo_path is not None:
shutil.rmtree(repo_path, ignore_errors=True)
if __name__ == "__main__":
configure_utf8_output()
try:
inspect_repo()
except subprocess.CalledProcessError as exc:
sys.exit(exc.returncode or 1)
except Exception as e:
print(f"\n❌ Error: {e}")
import traceback
traceback.print_exc()
print(f"\n❌ Error: {e}", file=sys.stderr)
traceback.print_exc(file=sys.stderr)
sys.exit(1)

76
scripts/tests/run-test-suite.js Normal file
View File

@@ -0,0 +1,76 @@
#!/usr/bin/env node
const { spawnSync } = require("child_process");
const NETWORK_TEST_ENV = "ENABLE_NETWORK_TESTS";
const ENABLED_VALUES = new Set(["1", "true", "yes", "on"]);
const LOCAL_TEST_COMMANDS = [
["scripts/tests/validate_skills_headings.test.js"],
["scripts/run-python.js", "scripts/tests/test_validate_skills_headings.py"],
];
const NETWORK_TEST_COMMANDS = [
["scripts/run-python.js", "scripts/tests/inspect_microsoft_repo.py"],
["scripts/run-python.js", "scripts/tests/test_comprehensive_coverage.py"],
];
function isNetworkTestsEnabled() {
const value = process.env[NETWORK_TEST_ENV];
if (!value) {
return false;
}
return ENABLED_VALUES.has(String(value).trim().toLowerCase());
}
function runNodeCommand(args) {
const result = spawnSync(process.execPath, args, { stdio: "inherit" });
if (result.error) {
throw result.error;
}
if (result.signal) {
process.kill(process.pid, result.signal);
}
if (typeof result.status !== "number") {
process.exit(1);
}
if (result.status !== 0) {
process.exit(result.status);
}
}
function runCommandSet(commands) {
for (const commandArgs of commands) {
runNodeCommand(commandArgs);
}
}
function main() {
const mode = process.argv[2];
if (mode === "--local") {
runCommandSet(LOCAL_TEST_COMMANDS);
return;
}
if (mode === "--network") {
runCommandSet(NETWORK_TEST_COMMANDS);
return;
}
runCommandSet(LOCAL_TEST_COMMANDS);
if (!isNetworkTestsEnabled()) {
console.log(
`[tests] Skipping network integration tests. Set ${NETWORK_TEST_ENV}=1 to enable.`,
);
return;
}
console.log(`[tests] ${NETWORK_TEST_ENV} enabled; running network integration tests.`);
runCommandSet(NETWORK_TEST_COMMANDS);
}
main();

94
scripts/tests/test_comprehensive_coverage.py
View File

@@ -5,14 +5,62 @@ Ensures all skills are captured and no directory name collisions exist.
"""
import re
import io
import shutil
import subprocess
import sys
import tempfile
import traceback
import uuid
from pathlib import Path
from collections import defaultdict
MS_REPO = "https://github.com/microsoft/skills.git"
def create_clone_target(prefix: str) -> Path:
"""Return a writable, non-existent path for git clone destination."""
repo_tmp_root = Path(__file__).resolve().parents[2] / ".tmp" / "tests"
candidate_roots = (repo_tmp_root, Path(tempfile.gettempdir()))
last_error: OSError | None = None
for root in candidate_roots:
try:
root.mkdir(parents=True, exist_ok=True)
probe_file = root / f".{prefix}write-probe-{uuid.uuid4().hex}.tmp"
with probe_file.open("xb"):
pass
probe_file.unlink()
return root / f"{prefix}{uuid.uuid4().hex}"
except OSError as exc:
last_error = exc
if last_error is not None:
raise last_error
raise OSError("Unable to determine clone destination")
def configure_utf8_output() -> None:
"""Best-effort UTF-8 stdout/stderr on Windows without dropping diagnostics."""
for stream_name in ("stdout", "stderr"):
stream = getattr(sys, stream_name)
try:
stream.reconfigure(encoding="utf-8", errors="backslashreplace")
continue
except Exception:
pass
buffer = getattr(stream, "buffer", None)
if buffer is not None:
setattr(
sys,
stream_name,
io.TextIOWrapper(
buffer, encoding="utf-8", errors="backslashreplace"
),
)
def extract_skill_name(skill_md_path: Path) -> str | None:
"""Extract the 'name' field from SKILL.md YAML frontmatter."""
try:
@@ -41,27 +89,35 @@ def analyze_skill_locations():
print("🔬 Comprehensive Skill Coverage & Uniqueness Analysis")
print("=" * 60)
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
repo_path: Path | None = None
try:
repo_path = create_clone_target(prefix="ms-skills-")
print("\n1️⃣ Cloning repository...")
subprocess.run(
["git", "clone", "--depth", "1", MS_REPO, str(temp_path)],
check=True,
capture_output=True,
)
try:
subprocess.run(
["git", "clone", "--depth", "1", MS_REPO, str(repo_path)],
check=True,
capture_output=True,
text=True,
)
except subprocess.CalledProcessError as exc:
print("\n❌ git clone failed.", file=sys.stderr)
if exc.stderr:
print(exc.stderr.strip(), file=sys.stderr)
raise
# Find ALL SKILL.md files
all_skill_files = list(temp_path.rglob("SKILL.md"))
all_skill_files = list(repo_path.rglob("SKILL.md"))
print(f"\n2️⃣ Total SKILL.md files found: {len(all_skill_files)}")
# Categorize by location
location_types = defaultdict(list)
for skill_file in all_skill_files:
path_str = str(skill_file)
if ".github/skills" in path_str:
path_str = skill_file.as_posix()
if ".github/skills/" in path_str:
location_types["github_skills"].append(skill_file)
elif ".github/plugins" in path_str:
elif ".github/plugins/" in path_str:
location_types["github_plugins"].append(skill_file)
elif "/skills/" in path_str:
location_types["skills_dir"].append(skill_file)
@@ -81,7 +137,7 @@ def analyze_skill_locations():
for skill_file in all_skill_files:
try:
rel = skill_file.parent.relative_to(temp_path)
rel = skill_file.parent.relative_to(repo_path)
except ValueError:
rel = skill_file.parent
@@ -163,9 +219,13 @@ def analyze_skill_locations():
"invalid_names": len(invalid_names),
"passed": is_pass,
}
finally:
if repo_path is not None:
shutil.rmtree(repo_path, ignore_errors=True)
if __name__ == "__main__":
configure_utf8_output()
try:
results = analyze_skill_locations()
@@ -176,14 +236,18 @@ if __name__ == "__main__":
if results["passed"]:
print("\n✅ V4 FLAT STRUCTURE IS VALID")
print(" All names are unique and valid directory names!")
sys.exit(0)
else:
print("\n⚠️ V4 FLAT STRUCTURE NEEDS FIXES")
if results["collisions"] > 0:
print(f" {results['collisions']} name collisions to resolve")
if results["invalid_names"] > 0:
print(f" {results['invalid_names']} invalid directory names")
sys.exit(1)
except subprocess.CalledProcessError as exc:
sys.exit(exc.returncode or 1)
except Exception as e:
print(f"\n❌ Error: {e}")
import traceback
traceback.print_exc()
print(f"\n❌ Error: {e}", file=sys.stderr)
traceback.print_exc(file=sys.stderr)
sys.exit(1)

27
scripts/update_readme.py
View File

@@ -1,7 +1,31 @@
#!/usr/bin/env python3
import io
import json
import os
import re
import sys
def configure_utf8_output() -> None:
"""Best-effort UTF-8 stdout/stderr on Windows without dropping diagnostics."""
if sys.platform != "win32":
return
for stream_name in ("stdout", "stderr"):
stream = getattr(sys, stream_name)
try:
stream.reconfigure(encoding="utf-8", errors="backslashreplace")
continue
except Exception:
pass
buffer = getattr(stream, "buffer", None)
if buffer is not None:
setattr(
sys,
stream_name,
io.TextIOWrapper(buffer, encoding="utf-8", errors="backslashreplace"),
)
def update_readme():
@@ -55,11 +79,12 @@ def update_readme():
content,
)
with open(readme_path, "w", encoding="utf-8") as f:
with open(readme_path, "w", encoding="utf-8", newline="\n") as f:
f.write(content)
print("✅ README.md updated successfully.")
if __name__ == "__main__":
configure_utf8_output()
update_readme()

76
scripts/validate_skills.py
View File

@@ -2,6 +2,29 @@ import os
import re
import argparse
import sys
import io
def configure_utf8_output() -> None:
"""Best-effort UTF-8 stdout/stderr on Windows without dropping diagnostics."""
if sys.platform != "win32":
return
for stream_name in ("stdout", "stderr"):
stream = getattr(sys, stream_name)
try:
stream.reconfigure(encoding="utf-8", errors="backslashreplace")
continue
except Exception:
pass
buffer = getattr(stream, "buffer", None)
if buffer is not None:
setattr(
sys,
stream_name,
io.TextIOWrapper(buffer, encoding="utf-8", errors="backslashreplace"),
)
WHEN_TO_USE_PATTERNS = [
re.compile(r"^##\s+When\s+to\s+Use", re.MULTILINE | re.IGNORECASE),
@@ -12,39 +35,37 @@ WHEN_TO_USE_PATTERNS = [
def has_when_to_use_section(content):
return any(pattern.search(content) for pattern in WHEN_TO_USE_PATTERNS)
import yaml
def parse_frontmatter(content, rel_path=None):
"""
Simple frontmatter parser using regex to avoid external dependencies.
Returns a dict of key-values.
Parse frontmatter using PyYAML for robustness.
Returns a dict of key-values and a list of error messages.
"""
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
if not fm_match:
return None, []
return None, ["Missing or malformed YAML frontmatter"]
fm_text = fm_match.group(1)
metadata = {}
lines = fm_text.split('\n')
fm_errors = []
for i, line in enumerate(lines):
if ':' in line:
key, val = line.split(':', 1)
metadata[key.strip()] = val.strip().strip('"').strip("'")
# Check for multi-line description issue (problem identification for the user)
if key.strip() == "description":
stripped_val = val.strip()
if (stripped_val.startswith('"') and stripped_val.endswith('"')) or \
(stripped_val.startswith("'") and stripped_val.endswith("'")):
if i + 1 < len(lines) and lines[i+1].startswith(' '):
fm_errors.append(f"description is wrapped in quotes but followed by indented lines. This causes YAML truncation.")
# Check for literal indicators wrapped in quotes
if stripped_val in ['"|"', "'>'", '"|"', "'>'"]:
fm_errors.append(f"description uses a block indicator {stripped_val} inside quotes. Remove quotes for proper YAML block behavior.")
return metadata, fm_errors
try:
metadata = yaml.safe_load(fm_text) or {}
# Identification of the specific regression issue for better reporting
if "description" in metadata:
desc = metadata["description"]
if not desc or (isinstance(desc, str) and not desc.strip()):
fm_errors.append("description field is empty or whitespace only.")
elif desc == "|":
fm_errors.append("description contains only the YAML block indicator '|', likely due to a parsing regression.")
return metadata, fm_errors
except yaml.YAMLError as e:
return None, [f"YAML Syntax Error: {e}"]
def validate_skills(skills_dir, strict_mode=False):
configure_utf8_output()
print(f"🔍 Validating skills in: {skills_dir}")
print(f"⚙️ Mode: {'STRICT (CI)' if strict_mode else 'Standard (Dev)'}")
@@ -90,12 +111,15 @@ def validate_skills(skills_dir, strict_mode=False):
elif metadata["name"] != os.path.basename(root):
errors.append(f"❌ {rel_path}: Name '{metadata['name']}' does not match folder name '{os.path.basename(root)}'")
if "description" not in metadata:
if "description" not in metadata or metadata["description"] is None:
errors.append(f"❌ {rel_path}: Missing 'description' in frontmatter")
else:
# agentskills-ref checks for short descriptions
if len(metadata["description"]) > 200:
errors.append(f"❌ {rel_path}: Description is oversized ({len(metadata['description'])} chars). Must be concise.")
desc = metadata["description"]
if not isinstance(desc, str):
errors.append(f"❌ {rel_path}: 'description' must be a string, got {type(desc).__name__}")
elif len(desc) > 300: # increased limit for multi-line support
errors.append(f"❌ {rel_path}: Description is oversized ({len(desc)} chars). Must be concise.")
# Risk Validation (Quality Bar)
if "risk" not in metadata:

8
skills/10-andruia-skill-smith/SKILL.MD
View File

@@ -3,12 +3,16 @@ id: 10-andruia-skill-smith
name: 10-andruia-skill-smith
description: "Ingeniero de Sistemas de Andru.ia. Diseña, redacta y despliega nuevas habilidades (skills) dentro del repositorio siguiendo el Estándar de Diamante."
category: andruia
risk: official
risk: safe
source: personal
date_added: "2026-02-25"
---
# 🔨 Andru.ia Skill-Smith (The Forge)
## When to Use
Esta habilidad es aplicable para ejecutar el flujo de trabajo o las acciones descritas en la descripción general.
## 📝 Descripción
Soy el Ingeniero de Sistemas de Andru.ia. Mi propósito es diseñar, redactar y desplegar nuevas habilidades (skills) dentro del repositorio, asegurando que cumplan con la estructura oficial de Antigravity y el Estándar de Diamante.
@@ -38,4 +42,4 @@ Generar el código para los siguientes archivos:
## ⚠️ Reglas de Oro
- **Prefijos Numéricos:** Asignar un número correlativo a la carpeta (ej. 11, 12, 13) para mantener el orden.
- **Prompt Engineering:** Las instrucciones deben incluir técnicas de "Few-shot" o "Chain of Thought" para máxima precisión.
- **Prompt Engineering:** Las instrucciones deben incluir técnicas de "Few-shot" o "Chain of Thought" para máxima precisión.

4
skills/ai-engineer/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: ai-engineer
description: |
description: Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent architectures.

6
skills/ai-product/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: ai-product
description: "Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ..."
description: Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt ...
risk: unknown
source: "vibeship-spawner-skills (Apache 2.0)"
date_added: "2026-02-27"
source: vibeship-spawner-skills (Apache 2.0)
date_added: '2026-02-27'
---
# AI Product Development

4
skills/analytics-tracking/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: analytics-tracking
description: >
description: Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Analytics Tracking & Measurement Strategy

1
skills/android_ui_verification/SKILL.md
View File

@@ -3,6 +3,7 @@ name: android_ui_verification
description: Automated end-to-end UI testing and verification on an Android Emulator using ADB.
risk: safe
source: community
date_added: "2026-02-28"
---
# Android UI Verification Skill

4
skills/angular/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: angular
description: >-
description: Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns.
risk: safe
source: self
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Angular Expert

4
skills/api-documenter/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: api-documenter
description: |
description: Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
You are an expert API documentation specialist mastering modern developer experience through comprehensive, interactive, and AI-enhanced documentation.

218
skills/apify-actor-development/SKILL.md Normal file
View File

@@ -0,0 +1,218 @@
---
name: apify-actor-development
description: "Develop, debug, and deploy Apify Actors - serverless cloud programs for web scraping, automation, and data processing. Use when creating new Actors, modifying existing ones, or troubleshooting Acto..."
---
# Apify Actor Development
**Important:** Before you begin, fill in the `generatedBy` property in the meta section of `.actor/actor.json`. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
## What are Apify Actors?
Actors are serverless programs inspired by the UNIX philosophy - programs that do one thing well and can be easily combined to build complex systems. They're packaged as Docker images and run in isolated containers in the cloud.
**Core Concepts:**
- Accept well-defined JSON input
- Perform isolated tasks (web scraping, automation, data processing)
- Produce structured JSON output to datasets and/or store data in key-value stores
- Can run from seconds to hours or even indefinitely
- Persist state and can be restarted
## Prerequisites & Setup (MANDATORY)
Before creating or modifying actors, verify that `apify` CLI is installed `apify --help`.
If it is not installed, use one of these methods (listed in order of preference):
```bash
# Preferred: install via a package manager (provides integrity checks)
npm install -g apify-cli
# Or (Mac): brew install apify-cli
```
> **Security note:** Do NOT install the CLI by piping remote scripts to a shell
> (e.g. `curl … | bash` or `irm … | iex`). Always use a package manager.
When the apify CLI is installed, check that it is logged in with:
```bash
apify info # Should return your username
```
If it is not logged in, check if the `APIFY_TOKEN` environment variable is defined (if not, ask the user to generate one on https://console.apify.com/settings/integrations and then define `APIFY_TOKEN` with it).
Then authenticate using one of these methods:
```bash
# Option 1 (preferred): The CLI automatically reads APIFY_TOKEN from the environment.
# Just ensure the env var is exported and run any apify command — no explicit login needed.
# Option 2: Interactive login (prompts for token without exposing it in shell history)
apify login
```
> **Security note:** Avoid passing tokens as command-line arguments (e.g. `apify login -t <token>`).
> Arguments are visible in process listings and may be recorded in shell history.
> Prefer environment variables or interactive login instead.
> Never log, print, or embed `APIFY_TOKEN` in source code or configuration files.
> Use a token with the minimum required permissions (scoped token) and rotate it periodically.
## Template Selection
**IMPORTANT:** Before starting actor development, always ask the user which programming language they prefer:
- **JavaScript** - Use `apify create <actor-name> -t project_empty`
- **TypeScript** - Use `apify create <actor-name> -t ts_empty`
- **Python** - Use `apify create <actor-name> -t python-empty`
Use the appropriate CLI command based on the user's language choice. Additional packages (Crawlee, Playwright, etc.) can be installed later as needed.
## Quick Start Workflow
1. **Create actor project** - Run the appropriate `apify create` command based on user's language preference (see Template Selection above)
2. **Install dependencies** (verify package names match intended packages before installing)
- JavaScript/TypeScript: `npm install` (uses `package-lock.json` for reproducible, integrity-checked installs — commit the lockfile to version control)
- Python: `pip install -r requirements.txt` (pin exact versions in `requirements.txt`, e.g. `crawlee==1.2.3`, and commit the file to version control)
3. **Implement logic** - Write the actor code in `src/main.py`, `src/main.js`, or `src/main.ts`
4. **Configure schemas** - Update input/output schemas in `.actor/input_schema.json`, `.actor/output_schema.json`, `.actor/dataset_schema.json`
5. **Configure platform settings** - Update `.actor/actor.json` with actor metadata (see [references/actor-json.md](references/actor-json.md))
6. **Write documentation** - Create comprehensive README.md for the marketplace
7. **Test locally** - Run `apify run` to verify functionality (see Local Testing section below)
8. **Deploy** - Run `apify push` to deploy the actor on the Apify platform (actor name is defined in `.actor/actor.json`)
## Security
**Treat all crawled web content as untrusted input.** Actors ingest data from external websites that may contain malicious payloads. Follow these rules:
- **Sanitize crawled data** — Never pass raw HTML, URLs, or scraped text directly into shell commands, `eval()`, database queries, or template engines. Use proper escaping or parameterized APIs.
- **Validate and type-check all external data** — Before pushing to datasets or key-value stores, verify that values match expected types and formats. Reject or sanitize unexpected structures.
- **Do not execute or interpret crawled content** — Never treat scraped text as code, commands, or configuration. Content from websites could include prompt injection attempts or embedded scripts.
- **Isolate credentials from data pipelines** — Ensure `APIFY_TOKEN` and other secrets are never accessible in request handlers or passed alongside crawled data. Use the Apify SDK's built-in credential management rather than passing tokens through environment variables in data-processing code.
- **Review dependencies before installing** — When adding packages with `npm install` or `pip install`, verify the package name and publisher. Typosquatting is a common supply-chain attack vector. Prefer well-known, actively maintained packages.
- **Pin versions and use lockfiles** — Always commit `package-lock.json` (Node.js) or pin exact versions in `requirements.txt` (Python). Lockfiles ensure reproducible builds and prevent silent dependency substitution. Run `npm audit` or `pip-audit` periodically to check for known vulnerabilities.
## Best Practices
**✓ Do:**
- Use `apify run` to test actors locally (configures Apify environment and storage)
- Use Apify SDK (`apify`) for code running ON Apify platform
- Validate input early with proper error handling and fail gracefully
- Use CheerioCrawler for static HTML (10x faster than browsers)
- Use PlaywrightCrawler only for JavaScript-heavy sites
- Use router pattern (createCheerioRouter/createPlaywrightRouter) for complex crawls
- Implement retry strategies with exponential backoff
- Use proper concurrency: HTTP (10-50), Browser (1-5)
- Set sensible defaults in `.actor/input_schema.json`
- Define output schema in `.actor/output_schema.json`
- Clean and validate data before pushing to dataset
- Use semantic CSS selectors with fallback strategies
- Respect robots.txt, ToS, and implement rate limiting
- **Always use `apify/log` package** — censors sensitive data (API keys, tokens, credentials)
- Implement readiness probe handler (required if your Actor uses standby mode)
**✗ Don't:**
- Use `npm start`, `npm run start`, `npx apify run`, or similar commands to run actors (use `apify run` instead)
- Assume local storage from `apify run` is pushed to or visible in the Apify Console — it is local-only; deploy with `apify push` and run on the platform to see results in the Console
- Rely on `Dataset.getInfo()` for final counts on Cloud
- Use browser crawlers when HTTP/Cheerio works
- Hard code values that should be in input schema or environment variables
- Skip input validation or error handling
- Overload servers - use appropriate concurrency and delays
- Scrape prohibited content or ignore Terms of Service
- Store personal/sensitive data unless explicitly permitted
- Use deprecated options like `requestHandlerTimeoutMillis` on CheerioCrawler (v3.x)
- Use `additionalHttpHeaders` - use `preNavigationHooks` instead
- Pass raw crawled content into shell commands, `eval()`, or code-generation functions
- Use `console.log()` or `print()` instead of the Apify logger — these bypass credential censoring
- Disable standby mode without explicit permission
## Logging
See [references/logging.md](references/logging.md) for complete logging documentation including available log levels and best practices for JavaScript/TypeScript and Python.
Check `usesStandbyMode` in `.actor/actor.json` - only implement if set to `true`.
## Commands
```bash
apify run # Run Actor locally
apify login # Authenticate account
apify push # Deploy to Apify platform (uses name from .actor/actor.json)
apify help # List all commands
```
**IMPORTANT:** Always use `apify run` to test actors locally. Do not use `npm run start`, `npm start`, `yarn start`, or other package manager commands - these will not properly configure the Apify environment and storage.
## Local Testing
When testing an actor locally with `apify run`, provide input data by creating a JSON file at:
```
storage/key_value_stores/default/INPUT.json
```
This file should contain the input parameters defined in your `.actor/input_schema.json`. The actor will read this input when running locally, mirroring how it receives input on the Apify platform.
**IMPORTANT - Local storage is NOT synced to the Apify Console:**
- Running `apify run` stores all data (datasets, key-value stores, request queues) **only on your local filesystem** in the `storage/` directory.
- This data is **never** automatically uploaded or pushed to the Apify platform. It exists only on your machine.
- To verify results on the Apify Console, you must deploy the Actor with `apify push` and then run it on the platform.
- Do **not** rely on checking the Apify Console to verify results from local runs — instead, inspect the local `storage/` directory or check the Actor's log output.
## Standby Mode
See [references/standby-mode.md](references/standby-mode.md) for complete standby mode documentation including readiness probe implementation for JavaScript/TypeScript and Python.
## Project Structure
```
.actor/
├── actor.json # Actor config: name, version, env vars, runtime
├── input_schema.json # Input validation & Console form definition
└── output_schema.json # Output storage and display templates
src/
└── main.js/ts/py # Actor entry point
storage/ # Local-only storage (NOT synced to Apify Console)
├── datasets/ # Output items (JSON objects)
├── key_value_stores/ # Files, config, INPUT
└── request_queues/ # Pending crawl requests
Dockerfile # Container image definition
```
## Actor Configuration
See [references/actor-json.md](references/actor-json.md) for complete actor.json structure and configuration options.
## Input Schema
See [references/input-schema.md](references/input-schema.md) for input schema structure and examples.
## Output Schema
See [references/output-schema.md](references/output-schema.md) for output schema structure, examples, and template variables.
## Dataset Schema
See [references/dataset-schema.md](references/dataset-schema.md) for dataset schema structure, configuration, and display properties.
## Key-Value Store Schema
See [references/key-value-store-schema.md](references/key-value-store-schema.md) for key-value store schema structure, collections, and configuration.
## Apify MCP Tools
If MCP server is configured, use these tools for documentation:
- `search-apify-docs` - Search documentation
- `fetch-apify-docs` - Get full doc pages
Otherwise, the MCP Server url: `https://mcp.apify.com/?tools=docs`.
## Resources
- [docs.apify.com/llms.txt](https://docs.apify.com/llms.txt) - Apify quick reference documentation
- [docs.apify.com/llms-full.txt](https://docs.apify.com/llms-full.txt) - Apify complete documentation
- [https://crawlee.dev/llms.txt](https://crawlee.dev/llms.txt) - Crawlee quick reference documentation
- [https://crawlee.dev/llms-full.txt](https://crawlee.dev/llms-full.txt) - Crawlee complete documentation
- [whitepaper.actor](https://raw.githubusercontent.com/apify/actor-whitepaper/refs/heads/master/README.md) - Complete Actor specification

66
skills/apify-actor-development/references/actor-json.md Normal file
View File

@@ -0,0 +1,66 @@
# Actor Configuration (actor.json)
The `.actor/actor.json` file contains the Actor's configuration including metadata, schema references, and platform settings.
## Structure
```json
{
"actorSpecification": 1,
"name": "project-name",
"title": "Project Title",
"description": "Actor description",
"version": "0.0",
"meta": {
"templateId": "template-id",
"generatedBy": "<FILL-IN-TOOL-AND-MODEL>"
},
"input": "./input_schema.json",
"output": "./output_schema.json",
"storages": {
"dataset": "./dataset_schema.json"
},
"dockerfile": "../Dockerfile"
}
```
## Example
```json
{
"actorSpecification": 1,
"name": "project-cheerio-crawler-javascript",
"title": "Project Cheerio Crawler Javascript",
"description": "Crawlee and Cheerio project in javascript.",
"version": "0.0",
"meta": {
"templateId": "js-crawlee-cheerio",
"generatedBy": "Claude Code with Claude Sonnet 4.5"
},
"input": "./input_schema.json",
"output": "./output_schema.json",
"storages": {
"dataset": "./dataset_schema.json"
},
"dockerfile": "../Dockerfile"
}
```
## Properties
- `actorSpecification` (integer, required) - Version of actor specification (currently 1)
- `name` (string, required) - Actor identifier (lowercase, hyphens allowed)
- `title` (string, required) - Human-readable title displayed in UI
- `description` (string, optional) - Actor description for marketplace
- `version` (string, required) - Semantic version number
- `meta` (object, optional) - Metadata about actor generation
- `templateId` (string) - ID of template used to create the actor
- `generatedBy` (string) - Tool and model name that generated/modified the actor (e.g., "Claude Code with Claude Sonnet 4.5")
- `input` (string, optional) - Path to input schema file
- `output` (string, optional) - Path to output schema file
- `storages` (object, optional) - Storage schema references
- `dataset` (string) - Path to dataset schema file
- `keyValueStore` (string) - Path to key-value store schema file
- `dockerfile` (string, optional) - Path to Dockerfile
**Important:** Always fill in the `generatedBy` property with the tool and model you're currently using (e.g., "Claude Code with Claude Sonnet 4.5") to help Apify improve documentation.

209
skills/apify-actor-development/references/dataset-schema.md Normal file
View File

@@ -0,0 +1,209 @@
# Dataset Schema Reference
The dataset schema defines how your Actor's output data is structured, transformed, and displayed in the Output tab in the Apify Console.
## Examples
### JavaScript and TypeScript
Consider an example Actor that calls `Actor.pushData()` to store data into dataset:
```javascript
import { Actor } from 'apify';
// Initialize the JavaScript SDK
await Actor.init();
/**
* Actor code
*/
await Actor.pushData({
numericField: 10,
pictureUrl: 'https://www.google.com/images/branding/googlelogo/2x/googlelogo_color_92x30dp.png',
linkUrl: 'https://google.com',
textField: 'Google',
booleanField: true,
dateField: new Date(),
arrayField: ['#hello', '#world'],
objectField: {},
});
// Exit successfully
await Actor.exit();
```
### Python
Consider an example Actor that calls `Actor.push_data()` to store data into dataset:
```python
# Dataset push example (Python)
import asyncio
from datetime import datetime
from apify import Actor
async def main():
await Actor.init()
# Actor code
await Actor.push_data({
'numericField': 10,
'pictureUrl': 'https://www.google.com/images/branding/googlelogo/2x/googlelogo_color_92x30dp.png',
'linkUrl': 'https://google.com',
'textField': 'Google',
'booleanField': True,
'dateField': datetime.now().isoformat(),
'arrayField': ['#hello', '#world'],
'objectField': {},
})
# Exit successfully
await Actor.exit()
if __name__ == '__main__':
asyncio.run(main())
```
## Configuration
To set up the Actor's output tab UI, reference a dataset schema file in `.actor/actor.json`:
```json
{
"actorSpecification": 1,
"name": "book-library-scraper",
"title": "Book Library Scraper",
"version": "1.0.0",
"storages": {
"dataset": "./dataset_schema.json"
}
}
```
Then create the dataset schema in `.actor/dataset_schema.json`:
```json
{
"actorSpecification": 1,
"fields": {},
"views": {
"overview": {
"title": "Overview",
"transformation": {
"fields": [
"pictureUrl",
"linkUrl",
"textField",
"booleanField",
"arrayField",
"objectField",
"dateField",
"numericField"
]
},
"display": {
"component": "table",
"properties": {
"pictureUrl": {
"label": "Image",
"format": "image"
},
"linkUrl": {
"label": "Link",
"format": "link"
},
"textField": {
"label": "Text",
"format": "text"
},
"booleanField": {
"label": "Boolean",
"format": "boolean"
},
"arrayField": {
"label": "Array",
"format": "array"
},
"objectField": {
"label": "Object",
"format": "object"
},
"dateField": {
"label": "Date",
"format": "date"
},
"numericField": {
"label": "Number",
"format": "number"
}
}
}
}
}
}
```
## Structure
```json
{
"actorSpecification": 1,
"fields": {},
"views": {
"<VIEW_NAME>": {
"title": "string (required)",
"description": "string (optional)",
"transformation": {
"fields": ["string (required)"],
"unwind": ["string (optional)"],
"flatten": ["string (optional)"],
"omit": ["string (optional)"],
"limit": "integer (optional)",
"desc": "boolean (optional)"
},
"display": {
"component": "table (required)",
"properties": {
"<FIELD_NAME>": {
"label": "string (optional)",
"format": "text|number|date|link|boolean|image|array|object (optional)"
}
}
}
}
}
}
```
## Properties
### Dataset Schema Properties
- `actorSpecification` (integer, required) - Specifies the version of dataset schema structure document (currently only version 1)
- `fields` (JSONSchema object, required) - Schema of one dataset object (use JsonSchema Draft 2020-12 or compatible)
- `views` (DatasetView object, required) - Object with API and UI views description
### DatasetView Properties
- `title` (string, required) - Visible in UI Output tab and API
- `description` (string, optional) - Only available in API response
- `transformation` (ViewTransformation object, required) - Data transformation applied when loading from Dataset API
- `display` (ViewDisplay object, required) - Output tab UI visualization definition
### ViewTransformation Properties
- `fields` (string[], required) - Fields to present in output (order matches column order)
- `unwind` (string[], optional) - Deconstructs nested children into parent object
- `flatten` (string[], optional) - Transforms nested object into flat structure
- `omit` (string[], optional) - Removes specified fields from output
- `limit` (integer, optional) - Maximum number of results (default: all)
- `desc` (boolean, optional) - Sort order (true = newest first)
### ViewDisplay Properties
- `component` (string, required) - Only `table` is available
- `properties` (Object, optional) - Keys matching `transformation.fields` with ViewDisplayProperty values
### ViewDisplayProperty Properties
- `label` (string, optional) - Table column header
- `format` (string, optional) - One of: `text`, `number`, `date`, `link`, `boolean`, `image`, `array`, `object`

66
skills/apify-actor-development/references/input-schema.md Normal file
View File

@@ -0,0 +1,66 @@
# Input Schema Reference
The input schema defines the input parameters for an Actor. It's a JSON object comprising various field types supported by the Apify platform.
## Structure
```json
{
"title": "<INPUT-SCHEMA-TITLE>",
"type": "object",
"schemaVersion": 1,
"properties": {
/* define input fields here */
},
"required": []
}
```
## Example
```json
{
"title": "E-commerce Product Scraper Input",
"type": "object",
"schemaVersion": 1,
"properties": {
"startUrls": {
"title": "Start URLs",
"type": "array",
"description": "URLs to start scraping from (category pages or product pages)",
"editor": "requestListSources",
"default": [{ "url": "https://example.com/category" }],
"prefill": [{ "url": "https://example.com/category" }]
},
"followVariants": {
"title": "Follow Product Variants",
"type": "boolean",
"description": "Whether to scrape product variants (different colors, sizes)",
"default": true
},
"maxRequestsPerCrawl": {
"title": "Max Requests per Crawl",
"type": "integer",
"description": "Maximum number of pages to scrape (0 = unlimited)",
"default": 1000,
"minimum": 0
},
"proxyConfiguration": {
"title": "Proxy Configuration",
"type": "object",
"description": "Proxy settings for anti-bot protection",
"editor": "proxy",
"default": { "useApifyProxy": false }
},
"locale": {
"title": "Locale",
"type": "string",
"description": "Language/country code for localized content",
"default": "cs",
"enum": ["cs", "en", "de", "sk"],
"enumTitles": ["Czech", "English", "German", "Slovak"]
}
},
"required": ["startUrls"]
}
```

129
skills/apify-actor-development/references/key-value-store-schema.md Normal file
View File

@@ -0,0 +1,129 @@
# Key-Value Store Schema Reference
The key-value store schema organizes keys into logical groups called collections for easier data management.
## Examples
### JavaScript and TypeScript
Consider an example Actor that calls `Actor.setValue()` to save records into the key-value store:
```javascript
import { Actor } from 'apify';
// Initialize the JavaScript SDK
await Actor.init();
/**
* Actor code
*/
await Actor.setValue('document-1', 'my text data', { contentType: 'text/plain' });
await Actor.setValue(`image-${imageID}`, imageBuffer, { contentType: 'image/jpeg' });
// Exit successfully
await Actor.exit();
```
### Python
Consider an example Actor that calls `Actor.set_value()` to save records into the key-value store:
```python
# Key-Value Store set example (Python)
import asyncio
from apify import Actor
async def main():
await Actor.init()
# Actor code
await Actor.set_value('document-1', 'my text data', content_type='text/plain')
image_id = '123' # example placeholder
image_buffer = b'...' # bytes buffer with image data
await Actor.set_value(f'image-{image_id}', image_buffer, content_type='image/jpeg')
# Exit successfully
await Actor.exit()
if __name__ == '__main__':
asyncio.run(main())
```
## Configuration
To configure the key-value store schema, reference a schema file in `.actor/actor.json`:
```json
{
"actorSpecification": 1,
"name": "data-collector",
"title": "Data Collector",
"version": "1.0.0",
"storages": {
"keyValueStore": "./key_value_store_schema.json"
}
}
```
Then create the key-value store schema in `.actor/key_value_store_schema.json`:
```json
{
"actorKeyValueStoreSchemaVersion": 1,
"title": "Key-Value Store Schema",
"collections": {
"documents": {
"title": "Documents",
"description": "Text documents stored by the Actor",
"keyPrefix": "document-"
},
"images": {
"title": "Images",
"description": "Images stored by the Actor",
"keyPrefix": "image-",
"contentTypes": ["image/jpeg"]
}
}
}
```
## Structure
```json
{
"actorKeyValueStoreSchemaVersion": 1,
"title": "string (required)",
"description": "string (optional)",
"collections": {
"<COLLECTION_NAME>": {
"title": "string (required)",
"description": "string (optional)",
"key": "string (conditional - use key OR keyPrefix)",
"keyPrefix": "string (conditional - use key OR keyPrefix)",
"contentTypes": ["string (optional)"],
"jsonSchema": "object (optional)"
}
}
}
```
## Properties
### Key-Value Store Schema Properties
- `actorKeyValueStoreSchemaVersion` (integer, required) - Version of key-value store schema structure document (currently only version 1)
- `title` (string, required) - Title of the schema
- `description` (string, optional) - Description of the schema
- `collections` (Object, required) - Object where each key is a collection ID and value is a Collection object
### Collection Properties
- `title` (string, required) - Collection title shown in UI tabs
- `description` (string, optional) - Description appearing in UI tooltips
- `key` (string, conditional) - Single specific key for this collection
- `keyPrefix` (string, conditional) - Prefix for keys included in this collection
- `contentTypes` (string[], optional) - Allowed content types for validation
- `jsonSchema` (object, optional) - JSON Schema Draft 07 format for `application/json` content type validation
Either `key` or `keyPrefix` must be specified for each collection, but not both.

50
skills/apify-actor-development/references/logging.md Normal file
View File

@@ -0,0 +1,50 @@
# Actor Logging Reference
## JavaScript and TypeScript
**ALWAYS use the `apify/log` package for logging** - This package contains critical security logic including censoring sensitive data (Apify tokens, API keys, credentials) to prevent accidental exposure in logs.
### Available Log Levels in `apify/log`
The Apify log package provides the following methods for logging:
- `log.debug()` - Debug level logs (detailed diagnostic information)
- `log.info()` - Info level logs (general informational messages)
- `log.warning()` - Warning level logs (warning messages for potentially problematic situations)
- `log.warningOnce()` - Warning level logs (same warning message logged only once)
- `log.error()` - Error level logs (error messages for failures)
- `log.exception()` - Exception level logs (for exceptions with stack traces)
- `log.perf()` - Performance level logs (performance metrics and timing information)
- `log.deprecated()` - Deprecation level logs (warnings about deprecated code)
- `log.softFail()` - Soft failure logs (non-critical failures that don't stop execution, e.g., input validation errors, skipped items)
- `log.internal()` - Internal level logs (internal/system messages)
### Best Practices
- Use `log.debug()` for detailed operation-level diagnostics (inside functions)
- Use `log.info()` for general informational messages (API requests, successful operations)
- Use `log.warning()` for potentially problematic situations (validation failures, unexpected states)
- Use `log.error()` for actual errors and failures
- Use `log.exception()` for caught exceptions with stack traces
## Python
**ALWAYS use `Actor.log` for logging** - This logger contains critical security logic including censoring sensitive data (Apify tokens, API keys, credentials) to prevent accidental exposure in logs.
### Available Log Levels
The Apify Actor logger provides the following methods for logging:
- `Actor.log.debug()` - Debug level logs (detailed diagnostic information)
- `Actor.log.info()` - Info level logs (general informational messages)
- `Actor.log.warning()` - Warning level logs (warning messages for potentially problematic situations)
- `Actor.log.error()` - Error level logs (error messages for failures)
- `Actor.log.exception()` - Exception level logs (for exceptions with stack traces)
### Best Practices
- Use `Actor.log.debug()` for detailed operation-level diagnostics (inside functions)
- Use `Actor.log.info()` for general informational messages (API requests, successful operations)
- Use `Actor.log.warning()` for potentially problematic situations (validation failures, unexpected states)
- Use `Actor.log.error()` for actual errors and failures
- Use `Actor.log.exception()` for caught exceptions with stack traces

49
skills/apify-actor-development/references/output-schema.md Normal file
View File

@@ -0,0 +1,49 @@
# Output Schema Reference
The Actor output schema builds upon the schemas for the dataset and key-value store. It specifies where an Actor stores its output and defines templates for accessing that output. Apify Console uses these output definitions to display run results.
## Structure
```json
{
"actorOutputSchemaVersion": 1,
"title": "<OUTPUT-SCHEMA-TITLE>",
"properties": {
/* define your outputs here */
}
}
```
## Example
```json
{
"actorOutputSchemaVersion": 1,
"title": "Output schema of the files scraper",
"properties": {
"files": {
"type": "string",
"title": "Files",
"template": "{{links.apiDefaultKeyValueStoreUrl}}/keys"
},
"dataset": {
"type": "string",
"title": "Dataset",
"template": "{{links.apiDefaultDatasetUrl}}/items"
}
}
}
```
## Output Schema Template Variables
- `links` (object) - Contains quick links to most commonly used URLs
- `links.publicRunUrl` (string) - Public run url in format `https://console.apify.com/view/runs/:runId`
- `links.consoleRunUrl` (string) - Console run url in format `https://console.apify.com/actors/runs/:runId`
- `links.apiRunUrl` (string) - API run url in format `https://api.apify.com/v2/actor-runs/:runId`
- `links.apiDefaultDatasetUrl` (string) - API url of default dataset in format `https://api.apify.com/v2/datasets/:defaultDatasetId`
- `links.apiDefaultKeyValueStoreUrl` (string) - API url of default key-value store in format `https://api.apify.com/v2/key-value-stores/:defaultKeyValueStoreId`
- `links.containerRunUrl` (string) - URL of a webserver running inside the run in format `https://<containerId>.runs.apify.net/`
- `run` (object) - Contains information about the run same as it is returned from the `GET Run` API endpoint
- `run.defaultDatasetId` (string) - ID of the default dataset
- `run.defaultKeyValueStoreId` (string) - ID of the default key-value store

61
skills/apify-actor-development/references/standby-mode.md Normal file
View File

@@ -0,0 +1,61 @@
# Actor Standby Mode Reference
## JavaScript and TypeScript
- **NEVER disable standby mode (`usesStandbyMode: false`) in `.actor/actor.json` without explicit permission** - Actor Standby mode solves this problem by letting you have the Actor ready in the background, waiting for the incoming HTTP requests. In a sense, the Actor behaves like a real-time web server or standard API server instead of running the logic once to process everything in batch. Always keep `usesStandbyMode: true` unless there is a specific documented reason to disable it
- **ALWAYS implement readiness probe handler for standby Actors** - Handle the `x-apify-container-server-readiness-probe` header at GET / endpoint to ensure proper Actor lifecycle management
You can recognize a standby Actor by checking the `usesStandbyMode` property in `.actor/actor.json`. Only implement the readiness probe if this property is set to `true`.
### Readiness Probe Implementation Example
```javascript
// Apify standby readiness probe at root path
app.get('/', (req, res) => {
res.writeHead(200, { 'Content-Type': 'text/plain' });
if (req.headers['x-apify-container-server-readiness-probe']) {
res.end('Readiness probe OK\n');
} else {
res.end('Actor is ready\n');
}
});
```
Key points:
- Detect the `x-apify-container-server-readiness-probe` header in incoming requests
- Respond with HTTP 200 status code for both readiness probe and normal requests
- This enables proper Actor lifecycle management in standby mode
## Python
- **NEVER disable standby mode (`usesStandbyMode: false`) in `.actor/actor.json` without explicit permission** - Actor Standby mode solves this problem by letting you have the Actor ready in the background, waiting for the incoming HTTP requests. In a sense, the Actor behaves like a real-time web server or standard API server instead of running the logic once to process everything in batch. Always keep `usesStandbyMode: true` unless there is a specific documented reason to disable it
- **ALWAYS implement readiness probe handler for standby Actors** - Handle the `x-apify-container-server-readiness-probe` header at GET / endpoint to ensure proper Actor lifecycle management
You can recognize a standby Actor by checking the `usesStandbyMode` property in `.actor/actor.json`. Only implement the readiness probe if this property is set to `true`.
### Readiness Probe Implementation Example
```python
# Apify standby readiness probe
from http.server import SimpleHTTPRequestHandler
class GetHandler(SimpleHTTPRequestHandler):
def do_GET(self):
# Handle Apify standby readiness probe
if 'x-apify-container-server-readiness-probe' in self.headers:
self.send_response(200)
self.end_headers()
self.wfile.write(b'Readiness probe OK')
return
self.send_response(200)
self.end_headers()
self.wfile.write(b'Actor is ready')
```
Key points:
- Detect the `x-apify-container-server-readiness-probe` header in incoming requests
- Respond with HTTP 200 status code for both readiness probe and normal requests
- This enables proper Actor lifecycle management in standby mode

184
skills/apify-actorization/SKILL.md Normal file
View File

@@ -0,0 +1,184 @@
---
name: apify-actorization
description: "Convert existing projects into Apify Actors - serverless cloud programs. Actorize JavaScript/TypeScript (SDK with Actor.init/exit), Python (async context manager), or any language (CLI wrapper). Us..."
---
# Apify Actorization
Actorization converts existing software into reusable serverless applications compatible with the Apify platform. Actors are programs packaged as Docker images that accept well-defined JSON input, perform an action, and optionally produce structured JSON output.
## Quick Start
1. Run `apify init` in project root
2. Wrap code with SDK lifecycle (see language-specific section below)
3. Configure `.actor/input_schema.json`
4. Test with `apify run --input '{"key": "value"}'`
5. Deploy with `apify push`
## When to Use This Skill
- Converting an existing project to run on Apify platform
- Adding Apify SDK integration to a project
- Wrapping a CLI tool or script as an Actor
- Migrating a Crawlee project to Apify
## Prerequisites
Verify `apify` CLI is installed:
```bash
apify --help
```
If not installed:
```bash
curl -fsSL https://apify.com/install-cli.sh | bash
# Or (Mac): brew install apify-cli
# Or (Windows): irm https://apify.com/install-cli.ps1 | iex
# Or: npm install -g apify-cli
```
Verify CLI is logged in:
```bash
apify info # Should return your username
```
If not logged in, check if `APIFY_TOKEN` environment variable is defined. If not, ask the user to generate one at https://console.apify.com/settings/integrations, then:
```bash
apify login -t $APIFY_TOKEN
```
## Actorization Checklist
Copy this checklist to track progress:
- [ ] Step 1: Analyze project (language, entry point, inputs, outputs)
- [ ] Step 2: Run `apify init` to create Actor structure
- [ ] Step 3: Apply language-specific SDK integration
- [ ] Step 4: Configure `.actor/input_schema.json`
- [ ] Step 5: Configure `.actor/output_schema.json` (if applicable)
- [ ] Step 6: Update `.actor/actor.json` metadata
- [ ] Step 7: Test locally with `apify run`
- [ ] Step 8: Deploy with `apify push`
## Step 1: Analyze the Project
Before making changes, understand the project:
1. **Identify the language** - JavaScript/TypeScript, Python, or other
2. **Find the entry point** - The main file that starts execution
3. **Identify inputs** - Command-line arguments, environment variables, config files
4. **Identify outputs** - Files, console output, API responses
5. **Check for state** - Does it need to persist data between runs?
## Step 2: Initialize Actor Structure
Run in the project root:
```bash
apify init
```
This creates:
- `.actor/actor.json` - Actor configuration and metadata
- `.actor/input_schema.json` - Input definition for the Apify Console
- `Dockerfile` (if not present) - Container image definition
## Step 3: Apply Language-Specific Changes
Choose based on your project's language:
- **JavaScript/TypeScript**: See [js-ts-actorization.md](references/js-ts-actorization.md)
- **Python**: See [python-actorization.md](references/python-actorization.md)
- **Other Languages (CLI-based)**: See [cli-actorization.md](references/cli-actorization.md)
### Quick Reference
| Language | Install | Wrap Code |
|----------|---------|-----------|
| JS/TS | `npm install apify` | `await Actor.init()` ... `await Actor.exit()` |
| Python | `pip install apify` | `async with Actor:` |
| Other | Use CLI in wrapper script | `apify actor:get-input` / `apify actor:push-data` |
## Steps 4-6: Configure Schemas
See [schemas-and-output.md](references/schemas-and-output.md) for detailed configuration of:
- Input schema (`.actor/input_schema.json`)
- Output schema (`.actor/output_schema.json`)
- Actor configuration (`.actor/actor.json`)
- State management (request queues, key-value stores)
Validate schemas against `@apify/json_schemas` npm package.
## Step 7: Test Locally
Run the actor with inline input (for JS/TS and Python actors):
```bash
apify run --input '{"startUrl": "https://example.com", "maxItems": 10}'
```
Or use an input file:
```bash
apify run --input-file ./test-input.json
```
**Important:** Always use `apify run`, not `npm start` or `python main.py`. The CLI sets up the proper environment and storage.
## Step 8: Deploy
```bash
apify push
```
This uploads and builds your actor on the Apify platform.
## Monetization (Optional)
After deploying, you can monetize your actor in the Apify Store. The recommended model is **Pay Per Event (PPE)**:
- Per result/item scraped
- Per page processed
- Per API call made
Configure PPE in the Apify Console under Actor > Monetization. Charge for events in your code with `await Actor.charge('result')`.
Other options: **Rental** (monthly subscription) or **Free** (open source).
## Pre-Deployment Checklist
- [ ] `.actor/actor.json` exists with correct name and description
- [ ] `.actor/actor.json` validates against `@apify/json_schemas` (`actor.schema.json`)
- [ ] `.actor/input_schema.json` defines all required inputs
- [ ] `.actor/input_schema.json` validates against `@apify/json_schemas` (`input.schema.json`)
- [ ] `.actor/output_schema.json` defines output structure (if applicable)
- [ ] `.actor/output_schema.json` validates against `@apify/json_schemas` (`output.schema.json`)
- [ ] `Dockerfile` is present and builds successfully
- [ ] `Actor.init()` / `Actor.exit()` wraps main code (JS/TS)
- [ ] `async with Actor:` wraps main code (Python)
- [ ] Inputs are read via `Actor.getInput()` / `Actor.get_input()`
- [ ] Outputs use `Actor.pushData()` or key-value store
- [ ] `apify run` executes successfully with test input
- [ ] `generatedBy` is set in actor.json meta section
## Apify MCP Tools
If MCP server is configured, use these tools for documentation:
- `search-apify-docs` - Search documentation
- `fetch-apify-docs` - Get full doc pages
Otherwise, the MCP Server url: `https://mcp.apify.com/?tools=docs`.
## Resources
- [Actorization Academy](https://docs.apify.com/academy/actorization) - Comprehensive guide
- [Apify SDK for JavaScript](https://docs.apify.com/sdk/js) - Full SDK reference
- [Apify SDK for Python](https://docs.apify.com/sdk/python) - Full SDK reference
- [Apify CLI Reference](https://docs.apify.com/cli) - CLI commands
- [Actor Specification](https://raw.githubusercontent.com/apify/actor-whitepaper/refs/heads/master/README.md) - Complete specification

81
skills/apify-actorization/references/cli-actorization.md Normal file
View File

@@ -0,0 +1,81 @@
# CLI-Based Actorization
For languages without an SDK (Go, Rust, Java, etc.), create a wrapper script that uses the Apify CLI.
## Create Wrapper Script
Create `start.sh` in project root:
```bash
#!/bin/bash
set -e
# Get input from Apify key-value store
INPUT=$(apify actor:get-input)
# Parse input values (adjust based on your input schema)
MY_PARAM=$(echo "$INPUT" | jq -r '.myParam // "default"')
# Run your application with the input
./your-application --param "$MY_PARAM"
# If your app writes to a file, push it to key-value store
# apify actor:set-value OUTPUT --contentType application/json < output.json
# Or push structured data to dataset
# apify actor:push-data '{"result": "value"}'
```
## Update Dockerfile
Reference the [cli-start template Dockerfile](https://github.com/apify/actor-templates/blob/master/templates/cli-start/Dockerfile) which includes the `ubi` utility for installing binaries from GitHub releases.
```dockerfile
FROM apify/actor-node:20
# Install ubi for easy GitHub release installation
RUN curl --silent --location \
https://raw.githubusercontent.com/houseabsolute/ubi/master/bootstrap/bootstrap-ubi.sh | sh
# Install your CLI tool from GitHub releases (example)
# RUN ubi --project your-org/your-tool --in /usr/local/bin
# Or install apify-cli and jq manually
RUN npm install -g apify-cli
RUN apt-get update && apt-get install -y jq
# Copy your application
COPY . .
# Build your application if needed
# RUN ./build.sh
# Make start script executable
RUN chmod +x start.sh
# Run the wrapper script
CMD ["./start.sh"]
```
## Testing CLI-Based Actors
For CLI-based actors (shell wrapper scripts), you may need to test the underlying application directly with mock input, as `apify run` requires a Node.js or Python entry point.
Test your wrapper script locally:
```bash
# Set up mock input
export INPUT='{"myParam": "test-value"}'
# Run wrapper script
./start.sh
```
## CLI Commands Reference
| Command | Description |
|---------|-------------|
| `apify actor:get-input` | Get input JSON from key-value store |
| `apify actor:set-value KEY` | Store value in key-value store |
| `apify actor:push-data JSON` | Push data to dataset |
| `apify actor:get-value KEY` | Retrieve value from key-value store |

111
skills/apify-actorization/references/js-ts-actorization.md Normal file
View File

@@ -0,0 +1,111 @@
# JavaScript/TypeScript Actorization
## Install the Apify SDK
```bash
npm install apify
```
## Wrap Main Code with Actor Lifecycle
```javascript
import { Actor } from 'apify';
// Initialize connection to Apify platform
await Actor.init();
// ============================================
// Your existing code goes here
// ============================================
// Example: Get input from Apify Console or API
const input = await Actor.getInput();
console.log('Input:', input);
// Example: Your crawler or processing logic
// const crawler = new PlaywrightCrawler({ ... });
// await crawler.run([input.startUrl]);
// Example: Push results to dataset
// await Actor.pushData({ result: 'data' });
// ============================================
// End of your code
// ============================================
// Graceful shutdown
await Actor.exit();
```
## Key Points
- `Actor.init()` configures storage to use Apify API when running on platform
- `Actor.exit()` handles graceful shutdown and cleanup
- Both calls must be awaited
- Local execution remains unchanged - the SDK automatically detects the environment
## Crawlee Projects
Crawlee projects require minimal changes - just wrap with Actor lifecycle:
```javascript
import { Actor } from 'apify';
import { PlaywrightCrawler } from 'crawlee';
await Actor.init();
// Get and validate input
const input = await Actor.getInput();
const {
startUrl = 'https://example.com',
maxItems = 100,
} = input ?? {};
let itemCount = 0;
const crawler = new PlaywrightCrawler({
requestHandler: async ({ page, request, pushData }) => {
if (itemCount >= maxItems) return;
const title = await page.title();
await pushData({ url: request.url, title });
itemCount++;
},
});
await crawler.run([startUrl]);
await Actor.exit();
```
## Express/HTTP Servers
For web servers, use standby mode in actor.json:
```json
{
"actorSpecification": 1,
"name": "my-api",
"usesStandbyMode": true
}
```
Then implement readiness probe. See [standby-mode.md](../../apify-actor-development/references/standby-mode.md).
## Batch Processing Scripts
```javascript
import { Actor } from 'apify';
await Actor.init();
const input = await Actor.getInput();
const items = input.items || [];
for (const item of items) {
const result = processItem(item);
await Actor.pushData(result);
}
await Actor.exit();
```

95
skills/apify-actorization/references/python-actorization.md Normal file
View File

@@ -0,0 +1,95 @@
# Python Actorization
## Install the Apify SDK
```bash
pip install apify
```
## Wrap Main Function with Actor Context Manager
```python
import asyncio
from apify import Actor
async def main() -> None:
async with Actor:
# ============================================
# Your existing code goes here
# ============================================
# Example: Get input from Apify Console or API
actor_input = await Actor.get_input()
print(f'Input: {actor_input}')
# Example: Your crawler or processing logic
# crawler = PlaywrightCrawler(...)
# await crawler.run([actor_input.get('startUrl')])
# Example: Push results to dataset
# await Actor.push_data({'result': 'data'})
# ============================================
# End of your code
# ============================================
if __name__ == '__main__':
asyncio.run(main())
```
## Key Points
- `async with Actor:` handles both initialization and cleanup
- Automatically manages platform event listeners and graceful shutdown
- Local execution remains unchanged - the SDK automatically detects the environment
## Crawlee Python Projects
```python
import asyncio
from apify import Actor
from crawlee.playwright_crawler import PlaywrightCrawler
async def main() -> None:
async with Actor:
# Get and validate input
actor_input = await Actor.get_input() or {}
start_url = actor_input.get('startUrl', 'https://example.com')
max_items = actor_input.get('maxItems', 100)
item_count = 0
async def request_handler(context):
nonlocal item_count
if item_count >= max_items:
return
title = await context.page.title()
await context.push_data({'url': context.request.url, 'title': title})
item_count += 1
crawler = PlaywrightCrawler(request_handler=request_handler)
await crawler.run([start_url])
if __name__ == '__main__':
asyncio.run(main())
```
## Batch Processing Scripts
```python
import asyncio
from apify import Actor
async def main() -> None:
async with Actor:
actor_input = await Actor.get_input() or {}
items = actor_input.get('items', [])
for item in items:
result = process_item(item)
await Actor.push_data(result)
if __name__ == '__main__':
asyncio.run(main())
```

140
skills/apify-actorization/references/schemas-and-output.md Normal file
View File

@@ -0,0 +1,140 @@
# Schemas and Output Configuration
## Input Schema
Map your application's inputs to `.actor/input_schema.json`. Validate against the JSON Schema from the `@apify/json_schemas` npm package (`input.schema.json`).
```json
{
"title": "My Actor Input",
"type": "object",
"schemaVersion": 1,
"properties": {
"startUrl": {
"title": "Start URL",
"type": "string",
"description": "The URL to start processing from",
"editor": "textfield",
"prefill": "https://example.com"
},
"maxItems": {
"title": "Max Items",
"type": "integer",
"description": "Maximum number of items to process",
"default": 100,
"minimum": 1
}
},
"required": ["startUrl"]
}
```
### Mapping Guidelines
- Command-line arguments → input schema properties
- Environment variables → input schema or Actor env vars in actor.json
- Config files → input schema with object/array types
- Flatten deeply nested structures for better UX
## Output Schema
Define output structure in `.actor/output_schema.json`. Validate against the JSON Schema from the `@apify/json_schemas` npm package (`output.schema.json`).
### For Table-Like Data (Multiple Items)
- Use `Actor.pushData()` (JS) or `Actor.push_data()` (Python)
- Each item becomes a row in the dataset
### For Single Files or Blobs
- Use key-value store: `Actor.setValue()` / `Actor.set_value()`
- Get the public URL and include it in the dataset:
```javascript
// Store file with public access
await Actor.setValue('report.pdf', pdfBuffer, { contentType: 'application/pdf' });
// Get the public URL
const storeInfo = await Actor.openKeyValueStore();
const publicUrl = `https://api.apify.com/v2/key-value-stores/${storeInfo.id}/records/report.pdf`;
// Include URL in dataset output
await Actor.pushData({ reportUrl: publicUrl });
```
### For Multiple Files with a Common Prefix (Collections)
```javascript
// Store multiple files with a prefix
for (const [name, data] of files) {
await Actor.setValue(`screenshots/${name}`, data, { contentType: 'image/png' });
}
// Files are accessible at: .../records/screenshots%2F{name}
```
## Actor Configuration (actor.json)
Configure `.actor/actor.json`. Validate against the JSON Schema from the `@apify/json_schemas` npm package (`actor.schema.json`).
```json
{
"actorSpecification": 1,
"name": "my-actor",
"title": "My Actor",
"description": "Brief description of what the actor does",
"version": "1.0.0",
"meta": {
"templateId": "ts_empty",
"generatedBy": "Claude Code with Claude Opus 4.5"
},
"input": "./input_schema.json",
"dockerfile": "../Dockerfile"
}
```
**Important:** Fill in the `generatedBy` property with the tool/model used.
## State Management
### Request Queue - For Pausable Task Processing
The request queue works for any task processing, not just web scraping. Use a dummy URL with custom `uniqueKey` and `userData` for non-URL tasks:
```javascript
const requestQueue = await Actor.openRequestQueue();
// Add tasks to the queue (works for any processing, not just URLs)
await requestQueue.addRequest({
url: 'https://placeholder.local', // Dummy URL for non-scraping tasks
uniqueKey: `task-${taskId}`, // Unique identifier for deduplication
userData: { itemId: 123, action: 'process' }, // Your custom task data
});
// Process tasks from the queue (with Crawlee)
const crawler = new BasicCrawler({
requestQueue,
requestHandler: async ({ request }) => {
const { itemId, action } = request.userData;
// Process your task using userData
await processTask(itemId, action);
},
});
await crawler.run();
// Or manually consume without Crawlee:
let request;
while ((request = await requestQueue.fetchNextRequest())) {
await processTask(request.userData);
await requestQueue.markRequestHandled(request);
}
```
### Key-Value Store - For Checkpoint State
```javascript
// Save state
await Actor.setValue('STATE', { processedCount: 100 });
// Restore state on restart
const state = await Actor.getValue('STATE') || { processedCount: 0 };
```

121
skills/apify-audience-analysis/SKILL.md Normal file
View File

@@ -0,0 +1,121 @@
---
name: apify-audience-analysis
description: Understand audience demographics, preferences, behavior patterns, and engagement quality across Facebook, Instagram, YouTube, and TikTok.
---
# Audience Analysis
Analyze and understand your audience using Apify Actors to extract follower demographics, engagement patterns, and behavior data from multiple platforms.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Identify audience analysis type (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the analysis script
- [ ] Step 5: Summarize findings
```
### Step 1: Identify Audience Analysis Type
Select the appropriate Actor based on analysis needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Facebook follower demographics | `apify/facebook-followers-following-scraper` | FB followers/following lists |
| Facebook engagement behavior | `apify/facebook-likes-scraper` | FB post likes analysis |
| Facebook video audience | `apify/facebook-reels-scraper` | FB Reels viewers |
| Facebook comment analysis | `apify/facebook-comments-scraper` | FB post/video comments |
| Facebook content engagement | `apify/facebook-posts-scraper` | FB post engagement metrics |
| Instagram audience sizing | `apify/instagram-profile-scraper` | IG profile demographics |
| Instagram location-based | `apify/instagram-search-scraper` | IG geo-tagged audience |
| Instagram tagged network | `apify/instagram-tagged-scraper` | IG tag network analysis |
| Instagram comprehensive | `apify/instagram-scraper` | Full IG audience data |
| Instagram API-based | `apify/instagram-api-scraper` | IG API access |
| Instagram follower counts | `apify/instagram-followers-count-scraper` | IG follower tracking |
| Instagram comment export | `apify/export-instagram-comments-posts` | IG comment bulk export |
| Instagram comment analysis | `apify/instagram-comment-scraper` | IG comment sentiment |
| YouTube viewer feedback | `streamers/youtube-comments-scraper` | YT comment analysis |
| YouTube channel audience | `streamers/youtube-channel-scraper` | YT channel subscribers |
| TikTok follower demographics | `clockworks/tiktok-followers-scraper` | TT follower lists |
| TikTok profile analysis | `clockworks/tiktok-profile-scraper` | TT profile demographics |
| TikTok comment analysis | `clockworks/tiktok-comments-scraper` | TT comment engagement |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `apify/facebook-followers-following-scraper`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Findings
After completion, report:
- Number of audience members/profiles analyzed
- File location and name
- Key demographic insights
- Suggested next steps (deeper analysis, segmentation)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-audience-analysis/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-audience-analysis-1.0.1';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

121
skills/apify-brand-reputation-monitoring/SKILL.md Normal file
View File

@@ -0,0 +1,121 @@
---
name: apify-brand-reputation-monitoring
description: "Track reviews, ratings, sentiment, and brand mentions across Google Maps, Booking.com, TripAdvisor, Facebook, Instagram, YouTube, and TikTok. Use when user asks to monitor brand reputation, analyze..."
---
# Brand Reputation Monitoring
Scrape reviews, ratings, and brand mentions from multiple platforms using Apify Actors.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Determine data source (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the monitoring script
- [ ] Step 5: Summarize results
```
### Step 1: Determine Data Source
Select the appropriate Actor based on user needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Google Maps reviews | `compass/crawler-google-places` | Business reviews, ratings |
| Google Maps review export | `compass/Google-Maps-Reviews-Scraper` | Dedicated review scraping |
| Booking.com hotels | `voyager/booking-scraper` | Hotel data, scores |
| Booking.com reviews | `voyager/booking-reviews-scraper` | Detailed hotel reviews |
| TripAdvisor reviews | `maxcopell/tripadvisor-reviews` | Attraction/restaurant reviews |
| Facebook reviews | `apify/facebook-reviews-scraper` | Page reviews |
| Facebook comments | `apify/facebook-comments-scraper` | Post comment monitoring |
| Facebook page metrics | `apify/facebook-pages-scraper` | Page ratings overview |
| Facebook reactions | `apify/facebook-likes-scraper` | Reaction type analysis |
| Instagram comments | `apify/instagram-comment-scraper` | Comment sentiment |
| Instagram hashtags | `apify/instagram-hashtag-scraper` | Brand hashtag monitoring |
| Instagram search | `apify/instagram-search-scraper` | Brand mention discovery |
| Instagram tagged posts | `apify/instagram-tagged-scraper` | Brand tag tracking |
| Instagram export | `apify/export-instagram-comments-posts` | Bulk comment export |
| Instagram comprehensive | `apify/instagram-scraper` | Full Instagram monitoring |
| Instagram API | `apify/instagram-api-scraper` | API-based monitoring |
| YouTube comments | `streamers/youtube-comments-scraper` | Video comment sentiment |
| TikTok comments | `clockworks/tiktok-comments-scraper` | TikTok sentiment |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `compass/crawler-google-places`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Results
After completion, report:
- Number of reviews/mentions found
- File location and name
- Key fields available
- Suggested next steps (sentiment analysis, filtering)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-brand-reputation-monitoring/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-brand-reputation-monitoring-1.1.1';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

131
skills/apify-competitor-intelligence/SKILL.md Normal file
View File

@@ -0,0 +1,131 @@
---
name: apify-competitor-intelligence
description: Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.
---
# Competitor Intelligence
Analyze competitors using Apify Actors to extract data from multiple platforms.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Identify competitor analysis type (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the analysis script
- [ ] Step 5: Summarize findings
```
### Step 1: Identify Competitor Analysis Type
Select the appropriate Actor based on analysis needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Competitor business data | `compass/crawler-google-places` | Location analysis |
| Competitor contact discovery | `poidata/google-maps-email-extractor` | Email extraction |
| Feature benchmarking | `compass/google-maps-extractor` | Detailed business data |
| Competitor review analysis | `compass/Google-Maps-Reviews-Scraper` | Review comparison |
| Hotel competitor data | `voyager/booking-scraper` | Hotel benchmarking |
| Hotel review comparison | `voyager/booking-reviews-scraper` | Review analysis |
| Competitor ad strategies | `apify/facebook-ads-scraper` | Ad creative analysis |
| Competitor page metrics | `apify/facebook-pages-scraper` | Page performance |
| Competitor content analysis | `apify/facebook-posts-scraper` | Post strategies |
| Competitor reels performance | `apify/facebook-reels-scraper` | Reels analysis |
| Competitor audience analysis | `apify/facebook-comments-scraper` | Comment sentiment |
| Competitor event monitoring | `apify/facebook-events-scraper` | Event tracking |
| Competitor audience overlap | `apify/facebook-followers-following-scraper` | Follower analysis |
| Competitor review benchmarking | `apify/facebook-reviews-scraper` | Review comparison |
| Competitor ad monitoring | `apify/facebook-search-scraper` | Ad discovery |
| Competitor profile metrics | `apify/instagram-profile-scraper` | Profile analysis |
| Competitor content monitoring | `apify/instagram-post-scraper` | Post tracking |
| Competitor engagement analysis | `apify/instagram-comment-scraper` | Comment analysis |
| Competitor reel performance | `apify/instagram-reel-scraper` | Reel metrics |
| Competitor growth tracking | `apify/instagram-followers-count-scraper` | Follower tracking |
| Comprehensive competitor data | `apify/instagram-scraper` | Full analysis |
| API-based competitor analysis | `apify/instagram-api-scraper` | API access |
| Competitor video analysis | `streamers/youtube-scraper` | Video metrics |
| Competitor sentiment analysis | `streamers/youtube-comments-scraper` | Comment sentiment |
| Competitor channel metrics | `streamers/youtube-channel-scraper` | Channel analysis |
| TikTok competitor analysis | `clockworks/tiktok-scraper` | TikTok data |
| Competitor video strategies | `clockworks/tiktok-video-scraper` | Video analysis |
| Competitor TikTok profiles | `clockworks/tiktok-profile-scraper` | Profile data |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `compass/crawler-google-places`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Findings
After completion, report:
- Number of competitors analyzed
- File location and name
- Key competitive insights
- Suggested next steps (deeper analysis, benchmarking)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-competitor-intelligence/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-competitor-intelligence-1.0.1';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

120
skills/apify-content-analytics/SKILL.md Normal file
View File

@@ -0,0 +1,120 @@
---
name: apify-content-analytics
description: Track engagement metrics, measure campaign ROI, and analyze content performance across Instagram, Facebook, YouTube, and TikTok.
---
# Content Analytics
Track and analyze content performance using Apify Actors to extract engagement metrics from multiple platforms.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Identify content analytics type (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the analytics script
- [ ] Step 5: Summarize findings
```
### Step 1: Identify Content Analytics Type
Select the appropriate Actor based on analytics needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Post engagement metrics | `apify/instagram-post-scraper` | Post performance |
| Reel performance | `apify/instagram-reel-scraper` | Reel analytics |
| Follower growth tracking | `apify/instagram-followers-count-scraper` | Growth metrics |
| Comment engagement | `apify/instagram-comment-scraper` | Comment analysis |
| Hashtag performance | `apify/instagram-hashtag-scraper` | Branded hashtags |
| Mention tracking | `apify/instagram-tagged-scraper` | Tag tracking |
| Comprehensive metrics | `apify/instagram-scraper` | Full data |
| API-based analytics | `apify/instagram-api-scraper` | API access |
| Facebook post performance | `apify/facebook-posts-scraper` | Post metrics |
| Reaction analysis | `apify/facebook-likes-scraper` | Engagement types |
| Facebook Reels metrics | `apify/facebook-reels-scraper` | Reels performance |
| Ad performance tracking | `apify/facebook-ads-scraper` | Ad analytics |
| Facebook comment analysis | `apify/facebook-comments-scraper` | Comment engagement |
| Page performance audit | `apify/facebook-pages-scraper` | Page metrics |
| YouTube video metrics | `streamers/youtube-scraper` | Video performance |
| YouTube Shorts analytics | `streamers/youtube-shorts-scraper` | Shorts performance |
| TikTok content metrics | `clockworks/tiktok-scraper` | TikTok analytics |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `apify/instagram-post-scraper`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Findings
After completion, report:
- Number of content pieces analyzed
- File location and name
- Key performance insights
- Suggested next steps (deeper analysis, content optimization)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-content-analytics/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-content-analytics-1.0.0';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

263
skills/apify-ecommerce/SKILL.md Normal file
View File

@@ -0,0 +1,263 @@
---
name: apify-ecommerce
description: "Scrape e-commerce data for pricing intelligence, customer reviews, and seller discovery across Amazon, Walmart, eBay, IKEA, and 50+ marketplaces. Use when user asks to monitor prices, track competi..."
---
# E-commerce Data Extraction
Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.
## Prerequisites
- `.env` file with `APIFY_TOKEN` (at `~/.claude/.env`)
- Node.js 20.6+ (for native `--env-file` support)
## Workflow Selection
| User Need | Workflow | Best For |
|-----------|----------|----------|
| Track prices, compare products | Workflow 1: Products & Pricing | Price monitoring, MAP compliance, competitor analysis. Add AI summary for insights. |
| Analyze reviews (sentiment or quality) | Workflow 2: Reviews | Brand perception, customer sentiment, quality issues, defect patterns |
| Find sellers across stores | Workflow 3: Sellers | Unauthorized resellers, vendor discovery via Google Shopping |
## Progress Tracking
```
Task Progress:
- [ ] Step 1: Select workflow and determine data source
- [ ] Step 2: Configure Actor input
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the extraction script
- [ ] Step 5: Summarize results
```
---
## Workflow 1: Products & Pricing
**Use case:** Extract product data, prices, and stock status. Track competitor prices, detect MAP violations, benchmark products, or research markets.
**Best for:** Pricing analysts, product managers, market researchers.
### Input Options
| Input Type | Field | Description |
|------------|-------|-------------|
| Product URLs | `detailsUrls` | Direct URLs to product pages (use object format) |
| Category URLs | `listingUrls` | URLs to category/search result pages |
| Keyword Search | `keyword` + `marketplaces` | Search term across selected marketplaces |
### Example - Product URLs
```json
{
"detailsUrls": [
{"url": "https://www.amazon.com/dp/B09V3KXJPB"},
{"url": "https://www.walmart.com/ip/123456789"}
],
"additionalProperties": true
}
```
### Example - Keyword Search
```json
{
"keyword": "Samsung Galaxy S24",
"marketplaces": ["www.amazon.com", "www.walmart.com"],
"additionalProperties": true,
"maxProductResults": 50
}
```
### Optional: AI Summary
Add these fields to get AI-generated insights:
| Field | Description |
|-------|-------------|
| `fieldsToAnalyze` | Data points to analyze: `["name", "offers", "brand", "description"]` |
| `customPrompt` | Custom analysis instructions |
**Example with AI summary:**
```json
{
"keyword": "robot vacuum",
"marketplaces": ["www.amazon.com"],
"maxProductResults": 50,
"additionalProperties": true,
"fieldsToAnalyze": ["name", "offers", "brand"],
"customPrompt": "Summarize price range and identify top brands"
}
```
### Output Fields
- `name` - Product name
- `url` - Product URL
- `offers.price` - Current price
- `offers.priceCurrency` - Currency code (may vary by seller region)
- `brand.slogan` - Brand name (nested in object)
- `image` - Product image URL
- Additional seller/stock info when `additionalProperties: true`
> **Note:** Currency may vary in results even for US searches, as prices reflect different seller regions.
---
## Workflow 2: Customer Reviews
**Use case:** Extract reviews for sentiment analysis, brand perception monitoring, or quality issue detection.
**Best for:** Brand managers, customer experience teams, QA teams, product managers.
### Input Options
| Input Type | Field | Description |
|------------|-------|-------------|
| Product URLs | `reviewListingUrls` | Product pages to extract reviews from |
| Keyword Search | `keywordReviews` + `marketplacesReviews` | Search for product reviews by keyword |
### Example - Extract Reviews from Product
```json
{
"reviewListingUrls": [
{"url": "https://www.amazon.com/dp/B09V3KXJPB"}
],
"sortReview": "Most recent",
"additionalReviewProperties": true,
"maxReviewResults": 500
}
```
### Example - Keyword Search
```json
{
"keywordReviews": "wireless earbuds",
"marketplacesReviews": ["www.amazon.com"],
"sortReview": "Most recent",
"additionalReviewProperties": true,
"maxReviewResults": 200
}
```
### Sort Options
- `Most recent` - Latest reviews first (recommended)
- `Most relevant` - Platform default relevance
- `Most helpful` - Highest voted reviews
- `Highest rated` - 5-star reviews first
- `Lowest rated` - 1-star reviews first
> **Note:** The `sortReview: "Lowest rated"` option may not work consistently across all marketplaces. For quality analysis, collect a large sample and filter by rating in post-processing.
### Quality Analysis Tips
- Set high `maxReviewResults` for statistical significance
- Look for recurring keywords: "broke", "defect", "quality", "returned"
- Filter results by rating if sorting doesn't work as expected
- Cross-reference with competitor products for benchmarking
---
## Workflow 3: Seller Intelligence
**Use case:** Find sellers across stores, discover unauthorized resellers, evaluate vendor options.
**Best for:** Brand protection teams, procurement, supply chain managers.
> **Note:** This workflow uses Google Shopping to find sellers across stores. Direct seller profile URLs are not reliably supported.
### Input Configuration
```json
{
"googleShoppingSearchKeyword": "Nike Air Max 90",
"scrapeSellersFromGoogleShopping": true,
"countryCode": "us",
"maxGoogleShoppingSellersPerProduct": 20,
"maxGoogleShoppingResults": 100
}
```
### Options
| Field | Description |
|-------|-------------|
| `googleShoppingSearchKeyword` | Product name to search |
| `scrapeSellersFromGoogleShopping` | Set to `true` to extract sellers |
| `scrapeProductsFromGoogleShopping` | Set to `true` to also extract product details |
| `countryCode` | Target country (e.g., `us`, `uk`, `de`) |
| `maxGoogleShoppingSellersPerProduct` | Max sellers per product |
| `maxGoogleShoppingResults` | Total result limit |
---
## Supported Marketplaces
### Amazon (20+ regions)
`www.amazon.com`, `www.amazon.co.uk`, `www.amazon.de`, `www.amazon.fr`, `www.amazon.it`, `www.amazon.es`, `www.amazon.ca`, `www.amazon.com.au`, `www.amazon.co.jp`, `www.amazon.in`, `www.amazon.com.br`, `www.amazon.com.mx`, `www.amazon.nl`, `www.amazon.pl`, `www.amazon.se`, `www.amazon.ae`, `www.amazon.sa`, `www.amazon.sg`, `www.amazon.com.tr`, `www.amazon.eg`
### Major US Retailers
`www.walmart.com`, `www.costco.com`, `www.costco.ca`, `www.homedepot.com`
### European Retailers
`allegro.pl`, `allegro.cz`, `allegro.sk`, `www.alza.cz`, `www.alza.sk`, `www.alza.de`, `www.alza.at`, `www.alza.hu`, `www.kaufland.de`, `www.kaufland.pl`, `www.kaufland.cz`, `www.kaufland.sk`, `www.kaufland.at`, `www.kaufland.fr`, `www.kaufland.it`, `www.cdiscount.com`
### IKEA (40+ country/language combinations)
Supports all major IKEA regional sites with multiple language options.
### Google Shopping
Use for seller discovery across multiple stores.
---
## Running the Extraction
### Step 1: Set Skill Path
```bash
SKILL_PATH=~/.claude/skills/apify-ecommerce
```
### Step 2: Run Script
**Quick answer (display in chat):**
```bash
node --env-file=~/.claude/.env $SKILL_PATH/reference/scripts/run_actor.js \
--actor "apify/e-commerce-scraping-tool" \
--input 'JSON_INPUT'
```
**CSV export:**
```bash
node --env-file=~/.claude/.env $SKILL_PATH/reference/scripts/run_actor.js \
--actor "apify/e-commerce-scraping-tool" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_filename.csv \
--format csv
```
**JSON export:**
```bash
node --env-file=~/.claude/.env $SKILL_PATH/reference/scripts/run_actor.js \
--actor "apify/e-commerce-scraping-tool" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_filename.json \
--format json
```
### Step 3: Summarize Results
Report:
- Number of items extracted
- File location (if exported)
- Key insights based on workflow:
- **Products:** Price range, outliers, MAP violations
- **Reviews:** Average rating, sentiment trends, quality issues
- **Sellers:** Seller count, unauthorized sellers found
---
## Error Handling
| Error | Solution |
|-------|----------|
| `APIFY_TOKEN not found` | Ensure `~/.claude/.env` contains `APIFY_TOKEN=your_token` |
| `Actor not found` | Verify Actor ID: `apify/e-commerce-scraping-tool` |
| `Run FAILED` | Check Apify console link in error output |
| `Timeout` | Reduce `maxProductResults` or increase `--timeout` |
| `No results` | Verify URLs are valid and accessible |
| `Invalid marketplace` | Check marketplace value matches supported list exactly |

3
skills/apify-ecommerce/reference/scripts/package.json Normal file
View File

@@ -0,0 +1,3 @@
{
"type": "module"
}

369
skills/apify-ecommerce/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,369 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output data.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-ecommerce-1.0.0';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., apify/e-commerce-scraping-tool) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 products
node --env-file=.env scripts/run_actor.js \\
--actor "apify/e-commerce-scraping-tool" \\
--input '{"keyword": "bluetooth headphones", "marketplaces": ["www.amazon.com"], "maxProductResults": 10}'
# Export prices to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "apify/e-commerce-scraping-tool" \\
--input '{"detailsUrls": ["https://amazon.com/dp/B09V3KXJPB"]}' \\
--output prices.csv --format csv
# Export reviews to JSON
node --env-file=.env scripts/run_actor.js \\
--actor "apify/e-commerce-scraping-tool" \\
--input '{"reviewListingUrls": ["https://amazon.com/dp/B09V3KXJPB"], "maxReviewResults": 100}' \\
--output reviews.json --format json
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

118
skills/apify-influencer-discovery/SKILL.md Normal file
View File

@@ -0,0 +1,118 @@
---
name: apify-influencer-discovery
description: Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.
---
# Influencer Discovery
Discover and analyze influencers across multiple platforms using Apify Actors.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Determine discovery source (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the discovery script
- [ ] Step 5: Summarize results
```
### Step 1: Determine Discovery Source
Select the appropriate Actor based on user needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Influencer profiles | `apify/instagram-profile-scraper` | Profile metrics, bio, follower counts |
| Find by hashtag | `apify/instagram-hashtag-scraper` | Discover influencers using specific hashtags |
| Reel engagement | `apify/instagram-reel-scraper` | Analyze reel performance and engagement |
| Discovery by niche | `apify/instagram-search-scraper` | Search for influencers by keyword/niche |
| Brand mentions | `apify/instagram-tagged-scraper` | Track who tags brands/products |
| Comprehensive data | `apify/instagram-scraper` | Full profile, posts, comments analysis |
| API-based discovery | `apify/instagram-api-scraper` | Fast API-based data extraction |
| Engagement analysis | `apify/export-instagram-comments-posts` | Export comments for sentiment analysis |
| Facebook content | `apify/facebook-posts-scraper` | Analyze Facebook post performance |
| Micro-influencers | `apify/facebook-groups-scraper` | Find influencers in niche groups |
| Influential pages | `apify/facebook-search-scraper` | Search for influential pages |
| YouTube creators | `streamers/youtube-channel-scraper` | Channel metrics and subscriber data |
| TikTok influencers | `clockworks/tiktok-scraper` | Comprehensive TikTok data extraction |
| TikTok (free) | `clockworks/free-tiktok-scraper` | Free TikTok data extractor |
| Live streamers | `clockworks/tiktok-live-scraper` | Discover live streaming influencers |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `apify/instagram-profile-scraper`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Results
After completion, report:
- Number of influencers found
- File location and name
- Key metrics available (followers, engagement rate, etc.)
- Suggested next steps (filtering, outreach, deeper analysis)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-influencer-discovery/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-influencer-discovery-1.0.0';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

120
skills/apify-lead-generation/SKILL.md Normal file
View File

@@ -0,0 +1,120 @@
---
name: apify-lead-generation
description: "Generates B2B/B2C leads by scraping Google Maps, websites, Instagram, TikTok, Facebook, LinkedIn, YouTube, and Google Search. Use when user asks to find leads, prospects, businesses, build lead lis..."
---
# Lead Generation
Scrape leads from multiple platforms using Apify Actors.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Determine lead source (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the lead finder script
- [ ] Step 5: Summarize results
```
### Step 1: Determine Lead Source
Select the appropriate Actor based on user needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Local businesses | `compass/crawler-google-places` | Restaurants, gyms, shops |
| Contact enrichment | `vdrmota/contact-info-scraper` | Emails, phones from URLs |
| Instagram profiles | `apify/instagram-profile-scraper` | Influencer discovery |
| Instagram posts/comments | `apify/instagram-scraper` | Posts, comments, hashtags, places |
| Instagram search | `apify/instagram-search-scraper` | Places, users, hashtags discovery |
| TikTok videos/hashtags | `clockworks/tiktok-scraper` | Comprehensive TikTok data extraction |
| TikTok hashtags/profiles | `clockworks/free-tiktok-scraper` | Free TikTok data extractor |
| TikTok user search | `clockworks/tiktok-user-search-scraper` | Find users by keywords |
| TikTok profiles | `clockworks/tiktok-profile-scraper` | Creator outreach |
| TikTok followers/following | `clockworks/tiktok-followers-scraper` | Audience analysis, segmentation |
| Facebook pages | `apify/facebook-pages-scraper` | Business contacts |
| Facebook page contacts | `apify/facebook-page-contact-information` | Extract emails, phones, addresses |
| Facebook groups | `apify/facebook-groups-scraper` | Buying intent signals |
| Facebook events | `apify/facebook-events-scraper` | Event networking, partnerships |
| Google Search | `apify/google-search-scraper` | Broad lead discovery |
| YouTube channels | `streamers/youtube-scraper` | Creator partnerships |
| Google Maps emails | `poidata/google-maps-email-extractor` | Direct email extraction |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `compass/crawler-google-places`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Results
After completion, report:
- Number of leads found
- File location and name
- Key fields available
- Suggested next steps (filtering, enrichment)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-lead-generation/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-lead-generation-1.1.11';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

119
skills/apify-market-research/SKILL.md Normal file
View File

@@ -0,0 +1,119 @@
---
name: apify-market-research
description: Analyze market conditions, geographic opportunities, pricing, consumer behavior, and product validation across Google Maps, Facebook, Instagram, Booking.com, and TripAdvisor.
---
# Market Research
Conduct market research using Apify Actors to extract data from multiple platforms.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Identify market research type (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the analysis script
- [ ] Step 5: Summarize findings
```
### Step 1: Identify Market Research Type
Select the appropriate Actor based on research needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Market density | `compass/crawler-google-places` | Location analysis |
| Geospatial analysis | `compass/google-maps-extractor` | Business mapping |
| Regional interest | `apify/google-trends-scraper` | Trend data |
| Pricing and demand | `apify/facebook-marketplace-scraper` | Market pricing |
| Event market | `apify/facebook-events-scraper` | Event analysis |
| Consumer needs | `apify/facebook-groups-scraper` | Group research |
| Market landscape | `apify/facebook-pages-scraper` | Business pages |
| Business density | `apify/facebook-page-contact-information` | Contact data |
| Cultural insights | `apify/facebook-photos-scraper` | Visual research |
| Niche targeting | `apify/instagram-hashtag-scraper` | Hashtag research |
| Hashtag stats | `apify/instagram-hashtag-stats` | Market sizing |
| Market activity | `apify/instagram-reel-scraper` | Activity analysis |
| Market intelligence | `apify/instagram-scraper` | Full data |
| Product launch research | `apify/instagram-api-scraper` | API access |
| Hospitality market | `voyager/booking-scraper` | Hotel data |
| Tourism insights | `maxcopell/tripadvisor-reviews` | Review analysis |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `compass/crawler-google-places`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Findings
After completion, report:
- Number of results found
- File location and name
- Key market insights
- Suggested next steps (deeper analysis, validation)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-market-research/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-market-research-1.0.0';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

122
skills/apify-trend-analysis/SKILL.md Normal file
View File

@@ -0,0 +1,122 @@
---
name: apify-trend-analysis
description: Discover and track emerging trends across Google Trends, Instagram, Facebook, YouTube, and TikTok to inform content strategy.
---
# Trend Analysis
Discover and track emerging trends using Apify Actors to extract data from multiple platforms.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Identify trend type (select Actor)
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the analysis script
- [ ] Step 5: Summarize findings
```
### Step 1: Identify Trend Type
Select the appropriate Actor based on research needs:
| User Need | Actor ID | Best For |
|-----------|----------|----------|
| Search trends | `apify/google-trends-scraper` | Google Trends data |
| Hashtag tracking | `apify/instagram-hashtag-scraper` | Hashtag content |
| Hashtag metrics | `apify/instagram-hashtag-stats` | Performance stats |
| Visual trends | `apify/instagram-post-scraper` | Post analysis |
| Trending discovery | `apify/instagram-search-scraper` | Search trends |
| Comprehensive tracking | `apify/instagram-scraper` | Full data |
| API-based trends | `apify/instagram-api-scraper` | API access |
| Engagement trends | `apify/export-instagram-comments-posts` | Comment tracking |
| Product trends | `apify/facebook-marketplace-scraper` | Marketplace data |
| Visual analysis | `apify/facebook-photos-scraper` | Photo trends |
| Community trends | `apify/facebook-groups-scraper` | Group monitoring |
| YouTube Shorts | `streamers/youtube-shorts-scraper` | Short-form trends |
| YouTube hashtags | `streamers/youtube-video-scraper-by-hashtag` | Hashtag videos |
| TikTok hashtags | `clockworks/tiktok-hashtag-scraper` | Hashtag content |
| Trending sounds | `clockworks/tiktok-sound-scraper` | Audio trends |
| TikTok ads | `clockworks/tiktok-ads-scraper` | Ad trends |
| Discover page | `clockworks/tiktok-discover-scraper` | Discover trends |
| Explore trends | `clockworks/tiktok-explore-scraper` | Explore content |
| Trending content | `clockworks/tiktok-trends-scraper` | Viral content |
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `apify/google-trends-scraper`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Findings
After completion, report:
- Number of results found
- File location and name
- Key trend insights
- Suggested next steps (deeper analysis, content opportunities)
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-trend-analysis/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-trend-analysis-1.0.0';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

230
skills/apify-ultimate-scraper/SKILL.md Normal file
View File

@@ -0,0 +1,230 @@
---
name: apify-ultimate-scraper
description: "Universal AI-powered web scraper for any platform. Scrape data from Instagram, Facebook, TikTok, YouTube, Google Maps, Google Search, Google Trends, Booking.com, and TripAdvisor. Use for lead gener..."
---
# Universal Web Scraper
AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your task.
## Prerequisites
(No need to check it upfront)
- `.env` file with `APIFY_TOKEN`
- Node.js 20.6+ (for native `--env-file` support)
- `mcpc` CLI tool: `npm install -g @apify/mcpc`
## Workflow
Copy this checklist and track progress:
```
Task Progress:
- [ ] Step 1: Understand user goal and select Actor
- [ ] Step 2: Fetch Actor schema via mcpc
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the scraper script
- [ ] Step 5: Summarize results and offer follow-ups
```
### Step 1: Understand User Goal and Select Actor
First, understand what the user wants to achieve. Then select the best Actor from the options below.
#### Instagram Actors (12)
| Actor ID | Best For |
|----------|----------|
| `apify/instagram-profile-scraper` | Profile data, follower counts, bio info |
| `apify/instagram-post-scraper` | Individual post details, engagement metrics |
| `apify/instagram-comment-scraper` | Comment extraction, sentiment analysis |
| `apify/instagram-hashtag-scraper` | Hashtag content, trending topics |
| `apify/instagram-hashtag-stats` | Hashtag performance metrics |
| `apify/instagram-reel-scraper` | Reels content and metrics |
| `apify/instagram-search-scraper` | Search users, places, hashtags |
| `apify/instagram-tagged-scraper` | Posts tagged with specific accounts |
| `apify/instagram-followers-count-scraper` | Follower count tracking |
| `apify/instagram-scraper` | Comprehensive Instagram data |
| `apify/instagram-api-scraper` | API-based Instagram access |
| `apify/export-instagram-comments-posts` | Bulk comment/post export |
#### Facebook Actors (14)
| Actor ID | Best For |
|----------|----------|
| `apify/facebook-pages-scraper` | Page data, metrics, contact info |
| `apify/facebook-page-contact-information` | Emails, phones, addresses from pages |
| `apify/facebook-posts-scraper` | Post content and engagement |
| `apify/facebook-comments-scraper` | Comment extraction |
| `apify/facebook-likes-scraper` | Reaction analysis |
| `apify/facebook-reviews-scraper` | Page reviews |
| `apify/facebook-groups-scraper` | Group content and members |
| `apify/facebook-events-scraper` | Event data |
| `apify/facebook-ads-scraper` | Ad creative and targeting |
| `apify/facebook-search-scraper` | Search results |
| `apify/facebook-reels-scraper` | Reels content |
| `apify/facebook-photos-scraper` | Photo extraction |
| `apify/facebook-marketplace-scraper` | Marketplace listings |
| `apify/facebook-followers-following-scraper` | Follower/following lists |
#### TikTok Actors (14)
| Actor ID | Best For |
|----------|----------|
| `clockworks/tiktok-scraper` | Comprehensive TikTok data |
| `clockworks/free-tiktok-scraper` | Free TikTok extraction |
| `clockworks/tiktok-profile-scraper` | Profile data |
| `clockworks/tiktok-video-scraper` | Video details and metrics |
| `clockworks/tiktok-comments-scraper` | Comment extraction |
| `clockworks/tiktok-followers-scraper` | Follower lists |
| `clockworks/tiktok-user-search-scraper` | Find users by keywords |
| `clockworks/tiktok-hashtag-scraper` | Hashtag content |
| `clockworks/tiktok-sound-scraper` | Trending sounds |
| `clockworks/tiktok-ads-scraper` | Ad content |
| `clockworks/tiktok-discover-scraper` | Discover page content |
| `clockworks/tiktok-explore-scraper` | Explore content |
| `clockworks/tiktok-trends-scraper` | Trending content |
| `clockworks/tiktok-live-scraper` | Live stream data |
#### YouTube Actors (5)
| Actor ID | Best For |
|----------|----------|
| `streamers/youtube-scraper` | Video data and metrics |
| `streamers/youtube-channel-scraper` | Channel information |
| `streamers/youtube-comments-scraper` | Comment extraction |
| `streamers/youtube-shorts-scraper` | Shorts content |
| `streamers/youtube-video-scraper-by-hashtag` | Videos by hashtag |
#### Google Maps Actors (4)
| Actor ID | Best For |
|----------|----------|
| `compass/crawler-google-places` | Business listings, ratings, contact info |
| `compass/google-maps-extractor` | Detailed business data |
| `compass/Google-Maps-Reviews-Scraper` | Review extraction |
| `poidata/google-maps-email-extractor` | Email discovery from listings |
#### Other Actors (6)
| Actor ID | Best For |
|----------|----------|
| `apify/google-search-scraper` | Google search results |
| `apify/google-trends-scraper` | Google Trends data |
| `voyager/booking-scraper` | Booking.com hotel data |
| `voyager/booking-reviews-scraper` | Booking.com reviews |
| `maxcopell/tripadvisor-reviews` | TripAdvisor reviews |
| `vdrmota/contact-info-scraper` | Contact enrichment from URLs |
---
#### Actor Selection by Use Case
| Use Case | Primary Actors |
|----------|---------------|
| **Lead Generation** | `compass/crawler-google-places`, `poidata/google-maps-email-extractor`, `vdrmota/contact-info-scraper` |
| **Influencer Discovery** | `apify/instagram-profile-scraper`, `clockworks/tiktok-profile-scraper`, `streamers/youtube-channel-scraper` |
| **Brand Monitoring** | `apify/instagram-tagged-scraper`, `apify/instagram-hashtag-scraper`, `compass/Google-Maps-Reviews-Scraper` |
| **Competitor Analysis** | `apify/facebook-pages-scraper`, `apify/facebook-ads-scraper`, `apify/instagram-profile-scraper` |
| **Content Analytics** | `apify/instagram-post-scraper`, `clockworks/tiktok-scraper`, `streamers/youtube-scraper` |
| **Trend Research** | `apify/google-trends-scraper`, `clockworks/tiktok-trends-scraper`, `apify/instagram-hashtag-stats` |
| **Review Analysis** | `compass/Google-Maps-Reviews-Scraper`, `voyager/booking-reviews-scraper`, `maxcopell/tripadvisor-reviews` |
| **Audience Analysis** | `apify/instagram-followers-count-scraper`, `clockworks/tiktok-followers-scraper`, `apify/facebook-followers-following-scraper` |
---
#### Multi-Actor Workflows
For complex tasks, chain multiple Actors:
| Workflow | Step 1 | Step 2 |
|----------|--------|--------|
| **Lead enrichment** | `compass/crawler-google-places` → | `vdrmota/contact-info-scraper` |
| **Influencer vetting** | `apify/instagram-profile-scraper` → | `apify/instagram-comment-scraper` |
| **Competitor deep-dive** | `apify/facebook-pages-scraper` → | `apify/facebook-posts-scraper` |
| **Local business analysis** | `compass/crawler-google-places` → | `compass/Google-Maps-Reviews-Scraper` |
#### Can't Find a Suitable Actor?
If none of the Actors above match the user's request, search the Apify Store directly:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call search-actors keywords:="SEARCH_KEYWORDS" limit:=10 offset:=0 category:="" | jq -r '.content[0].text'
```
Replace `SEARCH_KEYWORDS` with 1-3 simple terms (e.g., "LinkedIn profiles", "Amazon products", "Twitter").
### Step 2: Fetch Actor Schema
Fetch the Actor's input schema and details dynamically using mcpc:
```bash
export $(grep APIFY_TOKEN .env | xargs) && mcpc --json mcp.apify.com --header "Authorization: Bearer $APIFY_TOKEN" tools-call fetch-actor-details actor:="ACTOR_ID" | jq -r ".content"
```
Replace `ACTOR_ID` with the selected Actor (e.g., `compass/crawler-google-places`).
This returns:
- Actor description and README
- Required and optional input parameters
- Output fields (if available)
### Step 3: Ask User Preferences
Before running, ask:
1. **Output format**:
- **Quick answer** - Display top few results in chat (no file saved)
- **CSV** - Full export with all fields
- **JSON** - Full export in JSON format
2. **Number of results**: Based on character of use case
### Step 4: Run the Script
**Quick answer (display in chat, no file):**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT'
```
**CSV:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.csv \
--format csv
```
**JSON:**
```bash
node --env-file=.env ${CLAUDE_PLUGIN_ROOT}/reference/scripts/run_actor.js \
--actor "ACTOR_ID" \
--input 'JSON_INPUT' \
--output YYYY-MM-DD_OUTPUT_FILE.json \
--format json
```
### Step 5: Summarize Results and Offer Follow-ups
After completion, report:
- Number of results found
- File location and name
- Key fields available
- **Suggested follow-up workflows** based on results:
| If User Got | Suggest Next |
|-------------|--------------|
| Business listings | Enrich with `vdrmota/contact-info-scraper` or get reviews |
| Influencer profiles | Analyze engagement with comment scrapers |
| Competitor pages | Deep-dive with post/ad scrapers |
| Trend data | Validate with platform-specific hashtag scrapers |
## Error Handling
`APIFY_TOKEN not found` - Ask user to create `.env` with `APIFY_TOKEN=your_token`
`mcpc not found` - Ask user to install `npm install -g @apify/mcpc`
`Actor not found` - Check Actor ID spelling
`Run FAILED` - Ask user to check Apify console link in error output
`Timeout` - Reduce input size or increase `--timeout`

363
skills/apify-ultimate-scraper/reference/scripts/run_actor.js Normal file
View File

@@ -0,0 +1,363 @@
#!/usr/bin/env node
/**
* Apify Actor Runner - Runs Apify actors and exports results.
*
* Usage:
* # Quick answer (display in chat, no file saved)
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
*
* # Export to file
* node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}' --output leads.csv --format csv
*/
import { parseArgs } from 'node:util';
import { writeFileSync, statSync } from 'node:fs';
// User-Agent for tracking skill usage in Apify analytics
const USER_AGENT = 'apify-agent-skills/apify-ultimate-scraper-1.3.0';
// Parse command-line arguments
function parseCliArgs() {
const options = {
actor: { type: 'string', short: 'a' },
input: { type: 'string', short: 'i' },
output: { type: 'string', short: 'o' },
format: { type: 'string', short: 'f', default: 'csv' },
timeout: { type: 'string', short: 't', default: '600' },
'poll-interval': { type: 'string', default: '5' },
help: { type: 'boolean', short: 'h' },
};
const { values } = parseArgs({ options, allowPositionals: false });
if (values.help) {
printHelp();
process.exit(0);
}
if (!values.actor) {
console.error('Error: --actor is required');
printHelp();
process.exit(1);
}
if (!values.input) {
console.error('Error: --input is required');
printHelp();
process.exit(1);
}
return {
actor: values.actor,
input: values.input,
output: values.output,
format: values.format || 'csv',
timeout: parseInt(values.timeout, 10),
pollInterval: parseInt(values['poll-interval'], 10),
};
}
function printHelp() {
console.log(`
Apify Actor Runner - Run Apify actors and export results
Usage:
node --env-file=.env scripts/run_actor.js --actor ACTOR_ID --input '{}'
Options:
--actor, -a Actor ID (e.g., compass/crawler-google-places) [required]
--input, -i Actor input as JSON string [required]
--output, -o Output file path (optional - if not provided, displays quick answer)
--format, -f Output format: csv, json (default: csv)
--timeout, -t Max wait time in seconds (default: 600)
--poll-interval Seconds between status checks (default: 5)
--help, -h Show this help message
Output Formats:
JSON (all data) --output file.json --format json
CSV (all data) --output file.csv --format csv
Quick answer (no --output) - displays top 5 in chat
Examples:
# Quick answer - display top 5 in chat
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}'
# Export all data to CSV
node --env-file=.env scripts/run_actor.js \\
--actor "compass/crawler-google-places" \\
--input '{"searchStringsArray": ["coffee shops"], "locationQuery": "Seattle, USA"}' \\
--output leads.csv --format csv
`);
}
// Start an actor run and return { runId, datasetId }
async function startActor(token, actorId, inputJson) {
// Convert "author/actor" format to "author~actor" for API compatibility
const apiActorId = actorId.replace('/', '~');
const url = `https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}`;
let data;
try {
data = JSON.parse(inputJson);
} catch (e) {
console.error(`Error: Invalid JSON input: ${e.message}`);
process.exit(1);
}
const response = await fetch(url, {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'User-Agent': `${USER_AGENT}/start_actor`,
},
body: JSON.stringify(data),
});
if (response.status === 404) {
console.error(`Error: Actor '${actorId}' not found`);
process.exit(1);
}
if (!response.ok) {
const text = await response.text();
console.error(`Error: API request failed (${response.status}): ${text}`);
process.exit(1);
}
const result = await response.json();
return {
runId: result.data.id,
datasetId: result.data.defaultDatasetId,
};
}
// Poll run status until complete or timeout
async function pollUntilComplete(token, runId, timeout, interval) {
const url = `https://api.apify.com/v2/actor-runs/${runId}?token=${encodeURIComponent(token)}`;
const startTime = Date.now();
let lastStatus = null;
while (true) {
const response = await fetch(url);
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to get run status: ${text}`);
process.exit(1);
}
const result = await response.json();
const status = result.data.status;
// Only print when status changes
if (status !== lastStatus) {
console.log(`Status: ${status}`);
lastStatus = status;
}
if (['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(status)) {
return status;
}
const elapsed = (Date.now() - startTime) / 1000;
if (elapsed > timeout) {
console.error(`Warning: Timeout after ${timeout}s, actor still running`);
return 'TIMED-OUT';
}
await sleep(interval * 1000);
}
}
// Download dataset items
async function downloadResults(token, datasetId, outputPath, format) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/download_${format}`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
if (format === 'json') {
writeFileSync(outputPath, JSON.stringify(data, null, 2));
} else {
// CSV output
if (data.length > 0) {
const fieldnames = Object.keys(data[0]);
const csvLines = [fieldnames.join(',')];
for (const row of data) {
const values = fieldnames.map((key) => {
let value = row[key];
// Truncate long text fields
if (typeof value === 'string' && value.length > 200) {
value = value.slice(0, 200) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
value = JSON.stringify(value) || '';
}
// CSV escape: wrap in quotes if contains comma, quote, or newline
if (value === null || value === undefined) {
return '';
}
const strValue = String(value);
if (strValue.includes(',') || strValue.includes('"') || strValue.includes('\n')) {
return `"${strValue.replace(/"/g, '""')}"`;
}
return strValue;
});
csvLines.push(values.join(','));
}
writeFileSync(outputPath, csvLines.join('\n'));
} else {
writeFileSync(outputPath, '');
}
}
console.log(`Saved to: ${outputPath}`);
}
// Display top 5 results in chat format
async function displayQuickAnswer(token, datasetId) {
const url = `https://api.apify.com/v2/datasets/${datasetId}/items?token=${encodeURIComponent(token)}&format=json`;
const response = await fetch(url, {
headers: {
'User-Agent': `${USER_AGENT}/quick_answer`,
},
});
if (!response.ok) {
const text = await response.text();
console.error(`Error: Failed to download results: ${text}`);
process.exit(1);
}
const data = await response.json();
const total = data.length;
if (total === 0) {
console.log('\nNo results found.');
return;
}
// Display top 5
console.log(`\n${'='.repeat(60)}`);
console.log(`TOP 5 RESULTS (of ${total} total)`);
console.log('='.repeat(60));
for (let i = 0; i < Math.min(5, data.length); i++) {
const item = data[i];
console.log(`\n--- Result ${i + 1} ---`);
for (const [key, value] of Object.entries(item)) {
let displayValue = value;
// Truncate long values
if (typeof value === 'string' && value.length > 100) {
displayValue = value.slice(0, 100) + '...';
} else if (Array.isArray(value) || (typeof value === 'object' && value !== null)) {
const jsonStr = JSON.stringify(value);
displayValue = jsonStr.length > 100 ? jsonStr.slice(0, 100) + '...' : jsonStr;
}
console.log(` ${key}: ${displayValue}`);
}
}
console.log(`\n${'='.repeat(60)}`);
if (total > 5) {
console.log(`Showing 5 of ${total} results.`);
}
console.log(`Full data available at: https://console.apify.com/storage/datasets/${datasetId}`);
console.log('='.repeat(60));
}
// Report summary of downloaded data
function reportSummary(outputPath, format) {
const stats = statSync(outputPath);
const size = stats.size;
let count;
try {
const content = require('fs').readFileSync(outputPath, 'utf-8');
if (format === 'json') {
const data = JSON.parse(content);
count = Array.isArray(data) ? data.length : 1;
} else {
// CSV - count lines minus header
const lines = content.split('\n').filter((line) => line.trim());
count = Math.max(0, lines.length - 1);
}
} catch {
count = 'unknown';
}
console.log(`Records: ${count}`);
console.log(`Size: ${size.toLocaleString()} bytes`);
}
// Helper: sleep for ms
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// Main function
async function main() {
// Parse args first so --help works without token
const args = parseCliArgs();
// Check for APIFY_TOKEN
const token = process.env.APIFY_TOKEN;
if (!token) {
console.error('Error: APIFY_TOKEN not found in .env file');
console.error('');
console.error('Add your token to .env file:');
console.error(' APIFY_TOKEN=your_token_here');
console.error('');
console.error('Get your token: https://console.apify.com/account/integrations');
process.exit(1);
}
// Start the actor run
console.log(`Starting actor: ${args.actor}`);
const { runId, datasetId } = await startActor(token, args.actor, args.input);
console.log(`Run ID: ${runId}`);
console.log(`Dataset ID: ${datasetId}`);
// Poll for completion
const status = await pollUntilComplete(token, runId, args.timeout, args.pollInterval);
if (status !== 'SUCCEEDED') {
console.error(`Error: Actor run ${status}`);
console.error(`Details: https://console.apify.com/actors/runs/${runId}`);
process.exit(1);
}
// Determine output mode
if (args.output) {
// File output mode
await downloadResults(token, datasetId, args.output, args.format);
reportSummary(args.output, args.format);
} else {
// Quick answer mode - display in chat
await displayQuickAnswer(token, datasetId);
}
}
main().catch((err) => {
console.error(`Error: ${err.message}`);
process.exit(1);
});

4
skills/arm-cortex-expert/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: arm-cortex-expert
description: >
description: Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD).
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# @arm-cortex-expert

4
skills/azure-ai-agents-persistent-dotnet/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-agents-persistent-dotnet
description: |
description: Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure.AI.Agents.Persistent (.NET)

4
skills/azure-ai-agents-persistent-java/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-agents-persistent-java
description: |
description: Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Agents Persistent SDK for Java

4
skills/azure-ai-contentsafety-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-contentsafety-py
description: |
description: Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Content Safety SDK for Python

4
skills/azure-ai-contentunderstanding-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-contentunderstanding-py
description: |
description: Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Content Understanding SDK for Python

4
skills/azure-ai-document-intelligence-dotnet/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-document-intelligence-dotnet
description: |
description: Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure.AI.DocumentIntelligence (.NET)

4
skills/azure-ai-ml-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-ml-py
description: |
description: Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Machine Learning SDK v2 for Python

4
skills/azure-ai-openai-dotnet/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-openai-dotnet
description: |
description: Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure.AI.OpenAI (.NET)

4
skills/azure-ai-projects-dotnet/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-projects-dotnet
description: |
description: Azure AI Projects SDK for .NET. High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure.AI.Projects (.NET)

4
skills/azure-ai-projects-java/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-projects-java
description: |
description: Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Projects SDK for Java

4
skills/azure-ai-textanalytics-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-textanalytics-py
description: |
description: Azure AI Text Analytics SDK for sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP. Use for natural language processing on text.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Text Analytics SDK for Python

4
skills/azure-ai-transcription-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-transcription-py
description: |
description: Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Transcription SDK for Python

4
skills/azure-ai-translation-document-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-translation-document-py
description: |
description: Azure AI Document Translation SDK for batch translation of documents with format preservation. Use for translating Word, PDF, Excel, PowerPoint, and other document formats at scale.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Document Translation SDK for Python

4
skills/azure-ai-translation-text-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-translation-text-py
description: |
description: Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Text Translation SDK for Python

4
skills/azure-ai-vision-imageanalysis-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-vision-imageanalysis-py
description: |
description: Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI Vision Image Analysis SDK for Python

4
skills/azure-ai-voicelive-dotnet/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-voicelive-dotnet
description: |
description: Azure AI Voice Live SDK for .NET. Build real-time voice AI applications with bidirectional WebSocket communication.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure.AI.VoiceLive (.NET)

4
skills/azure-ai-voicelive-java/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-voicelive-java
description: |
description: Azure AI VoiceLive SDK for Java. Real-time bidirectional voice conversations with AI assistants using WebSocket.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure AI VoiceLive SDK for Java

4
skills/azure-ai-voicelive-ts/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-ai-voicelive-ts
description: |
description: Azure AI Voice Live SDK for JavaScript/TypeScript. Build real-time voice AI applications with bidirectional WebSocket communication.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# @azure/ai-voicelive (JavaScript/TypeScript)

4
skills/azure-appconfiguration-java/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-appconfiguration-java
description: |
description: Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure App Configuration SDK for Java

4
skills/azure-appconfiguration-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-appconfiguration-py
description: |
description: Azure App Configuration SDK for Python. Use for centralized configuration management, feature flags, and dynamic settings.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure App Configuration SDK for Python

4
skills/azure-compute-batch-java/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-compute-batch-java
description: |
description: Azure Batch SDK for Java. Run large-scale parallel and HPC batch jobs with pools, jobs, tasks, and compute nodes.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Batch SDK for Java

4
skills/azure-containerregistry-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-containerregistry-py
description: |
description: Azure Container Registry SDK for Python. Use for managing container images, artifacts, and repositories.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Container Registry SDK for Python

4
skills/azure-cosmos-java/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-cosmos-java
description: |
description: Azure Cosmos DB SDK for Java. NoSQL database operations with global distribution, multi-model support, and reactive patterns.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Cosmos DB SDK for Java

4
skills/azure-cosmos-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-cosmos-py
description: |
description: Azure Cosmos DB SDK for Python (NoSQL API). Use for document CRUD, queries, containers, and globally distributed data.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Cosmos DB SDK for Python

4
skills/azure-cosmos-rust/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-cosmos-rust
description: |
description: Azure Cosmos DB SDK for Rust (NoSQL API). Use for document CRUD, queries, containers, and globally distributed data.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Cosmos DB SDK for Rust

4
skills/azure-cosmos-ts/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-cosmos-ts
description: |
description: Azure Cosmos DB JavaScript/TypeScript SDK (@azure/cosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# @azure/cosmos (TypeScript/JavaScript)

4
skills/azure-data-tables-py/SKILL.md
View File

@@ -1,9 +1,9 @@
---
name: azure-data-tables-py
description: |
description: Azure Tables SDK for Python (Storage and Cosmos DB). Use for NoSQL key-value storage, entity CRUD, and batch operations.
risk: unknown
source: community
date_added: "2026-02-27"
date_added: '2026-02-27'
---
# Azure Tables SDK for Python

Some files were not shown because too many files have changed in this diff Show More