diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json index aedc6a0c..2ba43500 100644 --- a/.claude-plugin/plugin.json +++ b/.claude-plugin/plugin.json @@ -1,7 +1,7 @@ { "name": "antigravity-awesome-skills", "version": "9.7.0", - "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,361 supported skills.", + "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,362 supported skills.", "author": { "name": "sickn33 and contributors", "url": "https://github.com/sickn33/antigravity-awesome-skills" diff --git a/CATALOG.md b/CATALOG.md index e85e4912..14b8e432 100644 --- a/CATALOG.md +++ b/CATALOG.md @@ -2,7 +2,7 @@ Generated at: 2026-02-08T00:00:00.000Z -Total skills: 1375 +Total skills: 1376 ## architecture (88) @@ -980,7 +980,7 @@ Total skills: 1375 | `yann-lecun-tecnico` | Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervise... | persona, cnn, jepa, self-supervised, pytorch | persona, cnn, jepa, self-supervised, pytorch, yann, lecun, tecnico, sub, skill, cnica, de | | `youtube-summarizer` | Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks | video, summarization, transcription, youtube, content-analysis | video, summarization, transcription, youtube, content-analysis, summarizer, extract, transcripts, videos, generate, detailed, summaries | -## infrastructure (121) +## infrastructure (122) | Skill | Description | Tags | Triggers | | --- | --- | --- | --- | @@ -1073,6 +1073,7 @@ Total skills: 1375 | `ml-engineer` | Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. | ml | ml, engineer, pytorch, tensorflow, frameworks, implements, model, serving, feature, engineering, testing, monitoring | | `ml-pipeline-workflow` | Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment. | ml, pipeline | ml, pipeline, complete, mlops, orchestration, data, preparation, through, model, deployment | | `moodle-external-api-development` | This skill guides you through creating custom external web service APIs for Moodle LMS, following Moodle's external API framework and coding standards. | moodle, external, api | moodle, external, api, development, skill, guides, through, creating, custom, web, apis, lms | +| `multi-agent-task-orchestrator` | Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring | multi-agent, orchestration, task-routing, quality-gates, anti-duplication | multi-agent, orchestration, task-routing, quality-gates, anti-duplication, multi, agent, task, orchestrator, route, tasks, specialized | | `multi-cloud-architecture` | Decision framework and patterns for architecting applications across AWS, Azure, and GCP. | multi, cloud, architecture | multi, cloud, architecture, decision, framework, architecting, applications, aws, azure, gcp | | `native-data-fetching` | Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline supp... | native, data, fetching | native, data, fetching, implementing, debugging, any, network, request, api, call, covers, fetch | | `observability-monitoring-monitor-setup` | You are a monitoring and observability expert specializing in implementing comprehensive monitoring solutions. Set up metrics collection, distributed tracing... | observability, monitoring, monitor, setup | observability, monitoring, monitor, setup, specializing, implementing, solutions, set, up, metrics, collection, distributed | diff --git a/README.md b/README.md index 4bae6578..9503a5fb 100644 --- a/README.md +++ b/README.md @@ -1,13 +1,13 @@ - -# 🌌 Antigravity Awesome Skills: 1,375+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More + +# 🌌 Antigravity Awesome Skills: 1,376+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More -> **Installable GitHub library of 1,375+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.** +> **Installable GitHub library of 1,376+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.** Antigravity Awesome Skills is an installable GitHub library and npm installer for reusable `SKILL.md` playbooks. It is designed for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, Kiro, OpenCode, GitHub Copilot, and other AI coding assistants that benefit from structured operating instructions. Instead of collecting one-off prompt snippets, this repository gives you a searchable, installable catalog of skills, bundles, workflows, plugin-safe distributions, and practical docs that help agents perform recurring tasks with better context, stronger constraints, and clearer outputs. You can use this repo to install a broad multi-tool skill library, start from role-based bundles, or jump into workflow-driven execution for planning, coding, debugging, testing, security review, infrastructure, product work, and growth tasks. The root README is intentionally a high-signal landing page: understand what the project is, install it quickly, choose the right tool path, and then follow deeper docs only when you need them. -**Start here:** [Star the repo](https://github.com/sickn33/antigravity-awesome-skills/stargazers) · [Install in 1 minute](#installation) · [Choose your tool](#choose-your-tool) · [Best skills by tool](#best-skills-by-tool) · [📚 Browse 1,375+ Skills](#browse-1375-skills) · [Bundles](docs/users/bundles.md) · [Workflows](docs/users/workflows.md) · [Plugins for Claude Code and Codex](docs/users/plugins.md) +**Start here:** [Star the repo](https://github.com/sickn33/antigravity-awesome-skills/stargazers) · [Install in 1 minute](#installation) · [Choose your tool](#choose-your-tool) · [Best skills by tool](#best-skills-by-tool) · [📚 Browse 1,376+ Skills](#browse-1376-skills) · [Bundles](docs/users/bundles.md) · [Workflows](docs/users/workflows.md) · [Plugins for Claude Code and Codex](docs/users/plugins.md) [![GitHub stars](https://img.shields.io/badge/⭐%2031%2C000%2B%20Stars-gold?style=for-the-badge)](https://github.com/sickn33/antigravity-awesome-skills/stargazers) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) @@ -28,7 +28,7 @@ You can use this repo to install a broad multi-tool skill library, start from ro - **Installable, not just inspirational**: use `npx antigravity-awesome-skills` to put skills where your tool expects them. - **Built for major agent workflows**: Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, Kiro, OpenCode, Copilot, and more. -- **Broad coverage with real utility**: 1,375+ skills across development, testing, security, infrastructure, product, and marketing. +- **Broad coverage with real utility**: 1,376+ skills across development, testing, security, infrastructure, product, and marketing. - **Faster onboarding**: bundles and workflows reduce the time from "I found this repo" to "I used my first skill". - **Useful whether you want breadth or curation**: browse the full catalog, start with top bundles, or compare alternatives before installing. @@ -127,7 +127,7 @@ Start with [Bundles](docs/users/bundles.md) for role-based recommendations, [Wor ## Best Skills By Tool -If you want a faster answer than "browse all 1,375+ skills", start with a tool-specific guide: +If you want a faster answer than "browse all 1,376+ skills", start with a tool-specific guide: - **[Claude Code skills](docs/users/claude-code-skills.md)**: install paths, starter skills, prompt examples, and plugin marketplace flow. - **[Cursor skills](docs/users/cursor-skills.md)**: best starter skills for `.cursor/skills/`, UI-heavy work, and pair-programming flows. @@ -183,7 +183,7 @@ If Antigravity starts hitting context limits with too many active skills, the ac If you use OpenCode or another `.agents/skills` host, prefer a reduced install up front instead of copying the full library into a context-sensitive runtime. The installer now supports `--risk`, `--category`, and `--tags` so you can keep the installed set narrow. -## Browse 1,375+ Skills +## Browse 1,376+ Skills Use the root repo as a landing page, then jump into the deeper surface that matches your intent. @@ -530,6 +530,8 @@ We officially thank the following contributors for their help in making this rep - [@Elkidogz](https://github.com/Elkidogz) - [@qcwssss](https://github.com/qcwssss) - [@spideyashith](https://github.com/spideyashith) +- [@milkomida77](https://github.com/milkomida77) +- [@tomjwxf](https://github.com/tomjwxf) ## Star History diff --git a/apps/web-app/public/sitemap.xml b/apps/web-app/public/sitemap.xml index 1f083ce9..7733ff5e 100644 --- a/apps/web-app/public/sitemap.xml +++ b/apps/web-app/public/sitemap.xml @@ -6,6 +6,12 @@ daily 1.0 + + http://localhost/skill/multi-agent-task-orchestrator + 2026-04-06 + weekly + 0.7 + http://localhost/skill/python-pptx-generator 2026-04-06 @@ -240,10 +246,4 @@ weekly 0.7 - - http://localhost/skill/akf-trust-metadata - 2026-04-06 - weekly - 0.7 - diff --git a/apps/web-app/public/skills.json.backup b/apps/web-app/public/skills.json.backup index 14005a20..b3485bae 100644 --- a/apps/web-app/public/skills.json.backup +++ b/apps/web-app/public/skills.json.backup @@ -18653,6 +18653,28 @@ "reasons": [] } }, + { + "id": "multi-agent-task-orchestrator", + "path": "skills/multi-agent-task-orchestrator", + "category": "agent-orchestration", + "name": "multi-agent-task-orchestrator", + "description": "Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring", + "risk": "safe", + "source": "community", + "date_added": "2026-04-09", + "plugin": { + "targets": { + "codex": "supported", + "claude": "supported" + }, + "setup": { + "type": "none", + "summary": "", + "docs": null + }, + "reasons": [] + } + }, { "id": "multi-cloud-architecture", "path": "skills/multi-cloud-architecture", diff --git a/data/aliases.json b/data/aliases.json index 02295de2..d57ee91a 100644 --- a/data/aliases.json +++ b/data/aliases.json @@ -95,6 +95,7 @@ "machine-learning-pipeline": "machine-learning-ops-ml-pipeline", "microsoft-azure-dotnet": "microsoft-azure-webjobs-extensions-authentication-events-dotnet", "moodle-external-development": "moodle-external-api-development", + "multi-agent-orchestrator": "multi-agent-task-orchestrator", "multi-platform-apps": "multi-platform-apps-multi-platform", "observability-monitoring-setup": "observability-monitoring-monitor-setup", "observability-monitoring-implement": "observability-monitoring-slo-implement", diff --git a/data/bundles.json b/data/bundles.json index 87896c0c..ca6cd2f8 100644 --- a/data/bundles.json +++ b/data/bundles.json @@ -723,6 +723,7 @@ "memory-forensics", "ml-engineer", "ml-pipeline-workflow", + "multi-agent-task-orchestrator", "observability-engineer", "observability-monitoring-monitor-setup", "observability-monitoring-slo-implement", diff --git a/data/catalog.json b/data/catalog.json index 59614616..1bd76981 100644 --- a/data/catalog.json +++ b/data/catalog.json @@ -1,6 +1,6 @@ { "generatedAt": "2026-02-08T00:00:00.000Z", - "total": 1375, + "total": 1376, "skills": [ { "id": "00-andruia-consultant", @@ -20867,6 +20867,34 @@ ], "path": "skills/multi-agent-patterns/SKILL.md" }, + { + "id": "multi-agent-task-orchestrator", + "name": "multi-agent-task-orchestrator", + "description": "Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring", + "category": "infrastructure", + "tags": [ + "multi-agent", + "orchestration", + "task-routing", + "quality-gates", + "anti-duplication" + ], + "triggers": [ + "multi-agent", + "orchestration", + "task-routing", + "quality-gates", + "anti-duplication", + "multi", + "agent", + "task", + "orchestrator", + "route", + "tasks", + "specialized" + ], + "path": "skills/multi-agent-task-orchestrator/SKILL.md" + }, { "id": "multi-cloud-architecture", "name": "multi-cloud-architecture", diff --git a/data/plugin-compatibility.json b/data/plugin-compatibility.json index 352f906e..dc3974f6 100644 --- a/data/plugin-compatibility.json +++ b/data/plugin-compatibility.json @@ -16216,6 +16216,25 @@ }, "runtime_files": [] }, + { + "id": "multi-agent-task-orchestrator", + "path": "skills/multi-agent-task-orchestrator", + "targets": { + "codex": "supported", + "claude": "supported" + }, + "setup": { + "type": "none", + "summary": "", + "docs": null + }, + "reasons": [], + "blocked_reasons": { + "codex": [], + "claude": [] + }, + "runtime_files": [] + }, { "id": "multi-cloud-architecture", "path": "skills/multi-cloud-architecture", @@ -26287,10 +26306,10 @@ } ], "summary": { - "total_skills": 1375, + "total_skills": 1376, "supported": { - "codex": 1346, - "claude": 1361 + "codex": 1347, + "claude": 1362 }, "blocked": { "codex": 29, diff --git a/docs/integrations/jetski-cortex.md b/docs/integrations/jetski-cortex.md index ca363c45..f043daed 100644 --- a/docs/integrations/jetski-cortex.md +++ b/docs/integrations/jetski-cortex.md @@ -1,9 +1,9 @@ --- title: Jetski/Cortex + Gemini Integration Guide -description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.375+ skills." +description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.376+ skills." --- -# Jetski/Cortex + Gemini: safe integration with 1,1.375+ skills +# Jetski/Cortex + Gemini: safe integration with 1,1.376+ skills This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**. @@ -23,7 +23,7 @@ Never do: - concatenate all `SKILL.md` content into a single system prompt; - re-inject the entire library for **every** request. -With over 1,1.375 skills, this approach fills the context window before user messages are even added, causing truncation. +With over 1,1.376 skills, this approach fills the context window before user messages are even added, causing truncation. --- diff --git a/docs/integrations/jetski-gemini-loader/README.md b/docs/integrations/jetski-gemini-loader/README.md index 0f0e77d7..05c07768 100644 --- a/docs/integrations/jetski-gemini-loader/README.md +++ b/docs/integrations/jetski-gemini-loader/README.md @@ -20,7 +20,7 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`. - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`. -This pattern avoids context overflow when you have 1,375+ skills installed. +This pattern avoids context overflow when you have 1,376+ skills installed. --- diff --git a/docs/maintainers/repo-growth-seo.md b/docs/maintainers/repo-growth-seo.md index 5ffe1df2..234068ff 100644 --- a/docs/maintainers/repo-growth-seo.md +++ b/docs/maintainers/repo-growth-seo.md @@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t Preferred positioning: -> Installable GitHub library of 1,375+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants. +> Installable GitHub library of 1,376+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants. Key framing: @@ -20,7 +20,7 @@ Key framing: Preferred description: -> Installable GitHub library of 1,375+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections. +> Installable GitHub library of 1,376+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections. Preferred homepage: @@ -28,7 +28,7 @@ Preferred homepage: Preferred social preview: -- use a clean preview image that says `1,375+ Agentic Skills`; +- use a clean preview image that says `1,376+ Agentic Skills`; - mention Claude Code, Cursor, Codex CLI, and Gemini CLI; - avoid dense text and tiny logos that disappear in social cards. diff --git a/docs/maintainers/skills-update-guide.md b/docs/maintainers/skills-update-guide.md index 7ba0ada2..287d8617 100644 --- a/docs/maintainers/skills-update-guide.md +++ b/docs/maintainers/skills-update-guide.md @@ -69,7 +69,7 @@ For manual updates, you need: The update process refreshes: - Skills index (`skills_index.json`) - Web app skills data (`apps\web-app\public\skills.json`) -- All 1,375+ skills from the skills directory +- All 1,376+ skills from the skills directory ## When to Update diff --git a/docs/users/bundles.md b/docs/users/bundles.md index 2b1700ad..096b89b1 100644 --- a/docs/users/bundles.md +++ b/docs/users/bundles.md @@ -673,4 +673,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open --- -_Last updated: March 2026 | Total Skills: 1,375+ | Total Bundles: 37_ +_Last updated: March 2026 | Total Skills: 1,376+ | Total Bundles: 37_ diff --git a/docs/users/claude-code-skills.md b/docs/users/claude-code-skills.md index 4ef11468..e1bcff5a 100644 --- a/docs/users/claude-code-skills.md +++ b/docs/users/claude-code-skills.md @@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the ## Why use this repo for Claude Code -- It includes 1,375+ skills instead of a narrow single-domain starter pack. +- It includes 1,376+ skills instead of a narrow single-domain starter pack. - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow. - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata. - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin. diff --git a/docs/users/gemini-cli-skills.md b/docs/users/gemini-cli-skills.md index c229f96f..c110b1d3 100644 --- a/docs/users/gemini-cli-skills.md +++ b/docs/users/gemini-cli-skills.md @@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim - It installs directly into the expected Gemini skills path. - It includes both core software engineering skills and deeper agent/LLM-oriented skills. -- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,375+ files. +- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,376+ files. - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly. ## Install Gemini CLI Skills diff --git a/docs/users/kiro-integration.md b/docs/users/kiro-integration.md index ea9f63cc..462baf18 100644 --- a/docs/users/kiro-integration.md +++ b/docs/users/kiro-integration.md @@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines: Kiro's agentic capabilities are enhanced by skills that provide: -- **Domain expertise** across 1,375+ specialized areas +- **Domain expertise** across 1,376+ specialized areas - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS - **Workflow automation** for common development tasks - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture diff --git a/docs/users/usage.md b/docs/users/usage.md index 95ae7801..eb37704a 100644 --- a/docs/users/usage.md +++ b/docs/users/usage.md @@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l When you ran `npx antigravity-awesome-skills` or cloned the repository, you: -✅ **Downloaded 1,375+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`) +✅ **Downloaded 1,376+ skill files** to your computer (default: `~/.gemini/antigravity/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`) ✅ **Made them available** to your AI assistant ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting) @@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide **Analogy:** -- You installed a toolbox with 1,375+ tools (✅ done) +- You installed a toolbox with 1,376+ tools (✅ done) - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools" - You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin @@ -212,7 +212,7 @@ Let's actually use a skill right now. Follow these steps: ## Step 5: Picking Your First Skills (Practical Advice) -Don't try to use all 1,375+ skills at once. Here's a sensible approach: +Don't try to use all 1,376+ skills at once. Here's a sensible approach: If you want a tool-specific starting point before choosing skills, use: @@ -343,7 +343,7 @@ Usually no, but if your AI doesn't recognize a skill: ### "Can I load all skills into the model at once?" -No. Even though you have 1,375+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block. +No. Even though you have 1,376+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block. The intended pattern is: diff --git a/docs/users/visual-guide.md b/docs/users/visual-guide.md index 0f530c87..5dfb174d 100644 --- a/docs/users/visual-guide.md +++ b/docs/users/visual-guide.md @@ -34,7 +34,7 @@ antigravity-awesome-skills/ ├── 📄 CONTRIBUTING.md ← Contributor workflow ├── 📄 CATALOG.md ← Full generated catalog │ -├── 📁 skills/ ← 1,375+ skills live here +├── 📁 skills/ ← 1,376+ skills live here │ │ │ ├── 📁 brainstorming/ │ │ └── 📄 SKILL.md ← Skill definition @@ -47,7 +47,7 @@ antigravity-awesome-skills/ │ │ └── 📁 2d-games/ │ │ └── 📄 SKILL.md ← Nested skills also supported │ │ -│ └── ... (1,375+ total) +│ └── ... (1,376+ total) │ ├── 📁 apps/ │ └── 📁 web-app/ ← Interactive browser @@ -100,7 +100,7 @@ antigravity-awesome-skills/ ``` ┌─────────────────────────┐ - │ 1,375+ SKILLS │ + │ 1,376+ SKILLS │ └────────────┬────────────┘ │ ┌────────────────────────┼────────────────────────┐ @@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill │ ├── 📁 brainstorming/ │ │ ├── 📁 stripe-integration/ │ │ ├── 📁 react-best-practices/ │ -│ └── ... (1,375+ total) │ +│ └── ... (1,376+ total) │ └─────────────────────────────────────────┘ ``` diff --git a/package.json b/package.json index 3b092fde..3975e7ad 100644 --- a/package.json +++ b/package.json @@ -1,7 +1,7 @@ { "name": "antigravity-awesome-skills", "version": "9.7.0", - "description": "1,375+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.", + "description": "1,376+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.", "license": "MIT", "scripts": { "validate": "node tools/scripts/run-python.js tools/scripts/validate_skills.py", diff --git a/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json b/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json index aedc6a0c..2ba43500 100644 --- a/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json +++ b/plugins/antigravity-awesome-skills-claude/.claude-plugin/plugin.json @@ -1,7 +1,7 @@ { "name": "antigravity-awesome-skills", "version": "9.7.0", - "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,361 supported skills.", + "description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,362 supported skills.", "author": { "name": "sickn33 and contributors", "url": "https://github.com/sickn33/antigravity-awesome-skills" diff --git a/plugins/antigravity-awesome-skills-claude/skills/multi-agent-task-orchestrator/SKILL.md b/plugins/antigravity-awesome-skills-claude/skills/multi-agent-task-orchestrator/SKILL.md new file mode 100644 index 00000000..88dbffbb --- /dev/null +++ b/plugins/antigravity-awesome-skills-claude/skills/multi-agent-task-orchestrator/SKILL.md @@ -0,0 +1,157 @@ +--- +name: multi-agent-task-orchestrator +description: "Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring" +category: agent-orchestration +risk: safe +source: community +source_repo: milkomida77/guardian-agent-prompts +source_type: community +date_added: "2026-04-09" +author: milkomida77 +tags: [multi-agent, orchestration, task-routing, quality-gates, anti-duplication] +tools: [claude, cursor, gemini] +--- + +# Multi-Agent Task Orchestrator + +## Overview + +A production-tested pattern for coordinating multiple AI agents through a single orchestrator. Instead of letting agents work independently (and conflict), one orchestrator decomposes tasks, routes them to specialists, prevents duplicate work, and verifies results before marking anything done. Battle-tested across 10,000+ tasks over 6 months. + +## When to Use This Skill + +- Use when you have 3+ specialized agents that need to coordinate on complex tasks +- Use when agents are doing duplicate or conflicting work +- Use when you need audit trails showing who did what and when +- Use when agent output quality is inconsistent and needs verification gates + +## How It Works + +### Step 1: Define the Orchestrator Identity + +The orchestrator must know what it IS and what it IS NOT. This prevents it from doing work instead of delegating: + +``` +You are the Task Orchestrator. You NEVER do specialized work yourself. +You decompose tasks, delegate to the right agent, prevent conflicts, +and verify quality before marking anything done. + +WHAT YOU ARE NOT: +- NOT a code writer — delegate to code agents +- NOT a researcher — delegate to research agents +- NOT a tester — delegate to test agents +``` + +This "NOT-block" pattern reduces task drift by ~35% in production. + +### Step 2: Build a Task Registry + +Before assigning work, check if anyone is already doing this task: + +```python +import sqlite3 +from difflib import SequenceMatcher + +def check_duplicate(description, threshold=0.55): + conn = sqlite3.connect("task_registry.db") + c = conn.cursor() + c.execute("SELECT id, description, agent, status FROM tasks WHERE status IN ('pending', 'in_progress')") + for row in c.fetchall(): + ratio = SequenceMatcher(None, description.lower(), row[1].lower()).ratio() + if ratio >= threshold: + return {"id": row[0], "description": row[1], "agent": row[2]} + return None +``` + +### Step 3: Route Tasks to Specialists + +Use keyword scoring to match tasks to the best agent: + +```python +AGENTS = { + "code-architect": ["code", "implement", "function", "bug", "fix", "refactor", "api"], + "security-reviewer": ["security", "vulnerability", "audit", "cve", "injection"], + "researcher": ["research", "compare", "analyze", "benchmark", "evaluate"], + "doc-writer": ["document", "readme", "explain", "tutorial", "guide"], + "test-engineer": ["test", "coverage", "unittest", "pytest", "spec"], +} + +def route_task(description): + scores = {} + for agent, keywords in AGENTS.items(): + scores[agent] = sum(1 for kw in keywords if kw in description.lower()) + return max(scores, key=scores.get) if max(scores.values()) > 0 else "code-architect" +``` + +### Step 4: Enforce Quality Gates + +Agent output is a CLAIM. Test output is EVIDENCE. + +``` +After agent reports completion: +1. Were files actually modified? (git diff --stat) +2. Do tests pass? (npm test / pytest) +3. Were secrets introduced? (grep for API keys, tokens) +4. Did the build succeed? (npm run build) +5. Were only intended files touched? (scope check) + +Mark done ONLY after ALL checks pass. +``` + +### Step 5: Run 30-Minute Heartbeats + +``` +Every 30 minutes, ask: +1. "What have I DELEGATED in the last 30 minutes?" +2. If nothing → open the task backlog and assign the next task +3. Check for idle agents (no message in >30min on assigned task) +4. Relance idle agents or reassign their tasks +``` + +## Examples + +### Example 1: Delegating a Code Task + +``` +[ORCHESTRATOR -> code-architect] TASK: Add rate limiting to /api/users +SCOPE: src/middleware/rate-limit.ts only +VERIFICATION: npm test -- --grep "rate-limit" +DEADLINE: 30 minutes +``` + +### Example 2: Handling a Duplicate + +``` +User asks: "Fix the login bug" +Registry check: Task #47 "Fix authentication bug" is IN_PROGRESS by security-reviewer +Decision: SKIP — similar task already assigned (78% match) +Action: Notify user of existing task, wait for completion +``` + +## Best Practices + +- Always define NOT-blocks for every agent (what they must refuse to do) +- Use SQLite for the task registry (lightweight, no server needed) +- Set similarity threshold at 55% for anti-duplication (lower = too many false positives) +- Require evidence-based quality gates (not just agent claims) +- Log every delegation with: task ID, agent, scope, deadline, verification command + +## Common Pitfalls + +- **Problem:** Orchestrator starts doing work instead of delegating + **Solution:** Add explicit NOT-blocks and role boundaries + +- **Problem:** Two agents modify the same file simultaneously + **Solution:** Task registry with file-level locking and queue system + +- **Problem:** Agent claims "done" without actual changes + **Solution:** Quality gate checks git diff before accepting completion + +- **Problem:** Tasks pile up without progress + **Solution:** 30-minute heartbeat catches stale assignments and reassigns + +## Related Skills + +- `@code-review` - For reviewing code changes after delegation +- `@test-driven-development` - For ensuring quality in agent output +- `@project-management` - For tracking multi-agent project progress diff --git a/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json b/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json index 6522bdc9..4088fe43 100644 --- a/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json +++ b/plugins/antigravity-awesome-skills/.codex-plugin/plugin.json @@ -19,7 +19,7 @@ "skills": "./skills/", "interface": { "displayName": "Antigravity Awesome Skills", - "shortDescription": "1,346 plugin-safe skills for coding, security, product, and ops workflows.", + "shortDescription": "1,347 plugin-safe skills for coding, security, product, and ops workflows.", "longDescription": "Install a plugin-safe Codex distribution of Antigravity Awesome Skills. Skills that still need hardening or target-specific setup remain available in the repo but are excluded from this plugin.", "developerName": "sickn33 and contributors", "category": "Productivity", diff --git a/plugins/antigravity-awesome-skills/skills/multi-agent-task-orchestrator/SKILL.md b/plugins/antigravity-awesome-skills/skills/multi-agent-task-orchestrator/SKILL.md new file mode 100644 index 00000000..88dbffbb --- /dev/null +++ b/plugins/antigravity-awesome-skills/skills/multi-agent-task-orchestrator/SKILL.md @@ -0,0 +1,157 @@ +--- +name: multi-agent-task-orchestrator +description: "Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring" +category: agent-orchestration +risk: safe +source: community +source_repo: milkomida77/guardian-agent-prompts +source_type: community +date_added: "2026-04-09" +author: milkomida77 +tags: [multi-agent, orchestration, task-routing, quality-gates, anti-duplication] +tools: [claude, cursor, gemini] +--- + +# Multi-Agent Task Orchestrator + +## Overview + +A production-tested pattern for coordinating multiple AI agents through a single orchestrator. Instead of letting agents work independently (and conflict), one orchestrator decomposes tasks, routes them to specialists, prevents duplicate work, and verifies results before marking anything done. Battle-tested across 10,000+ tasks over 6 months. + +## When to Use This Skill + +- Use when you have 3+ specialized agents that need to coordinate on complex tasks +- Use when agents are doing duplicate or conflicting work +- Use when you need audit trails showing who did what and when +- Use when agent output quality is inconsistent and needs verification gates + +## How It Works + +### Step 1: Define the Orchestrator Identity + +The orchestrator must know what it IS and what it IS NOT. This prevents it from doing work instead of delegating: + +``` +You are the Task Orchestrator. You NEVER do specialized work yourself. +You decompose tasks, delegate to the right agent, prevent conflicts, +and verify quality before marking anything done. + +WHAT YOU ARE NOT: +- NOT a code writer — delegate to code agents +- NOT a researcher — delegate to research agents +- NOT a tester — delegate to test agents +``` + +This "NOT-block" pattern reduces task drift by ~35% in production. + +### Step 2: Build a Task Registry + +Before assigning work, check if anyone is already doing this task: + +```python +import sqlite3 +from difflib import SequenceMatcher + +def check_duplicate(description, threshold=0.55): + conn = sqlite3.connect("task_registry.db") + c = conn.cursor() + c.execute("SELECT id, description, agent, status FROM tasks WHERE status IN ('pending', 'in_progress')") + for row in c.fetchall(): + ratio = SequenceMatcher(None, description.lower(), row[1].lower()).ratio() + if ratio >= threshold: + return {"id": row[0], "description": row[1], "agent": row[2]} + return None +``` + +### Step 3: Route Tasks to Specialists + +Use keyword scoring to match tasks to the best agent: + +```python +AGENTS = { + "code-architect": ["code", "implement", "function", "bug", "fix", "refactor", "api"], + "security-reviewer": ["security", "vulnerability", "audit", "cve", "injection"], + "researcher": ["research", "compare", "analyze", "benchmark", "evaluate"], + "doc-writer": ["document", "readme", "explain", "tutorial", "guide"], + "test-engineer": ["test", "coverage", "unittest", "pytest", "spec"], +} + +def route_task(description): + scores = {} + for agent, keywords in AGENTS.items(): + scores[agent] = sum(1 for kw in keywords if kw in description.lower()) + return max(scores, key=scores.get) if max(scores.values()) > 0 else "code-architect" +``` + +### Step 4: Enforce Quality Gates + +Agent output is a CLAIM. Test output is EVIDENCE. + +``` +After agent reports completion: +1. Were files actually modified? (git diff --stat) +2. Do tests pass? (npm test / pytest) +3. Were secrets introduced? (grep for API keys, tokens) +4. Did the build succeed? (npm run build) +5. Were only intended files touched? (scope check) + +Mark done ONLY after ALL checks pass. +``` + +### Step 5: Run 30-Minute Heartbeats + +``` +Every 30 minutes, ask: +1. "What have I DELEGATED in the last 30 minutes?" +2. If nothing → open the task backlog and assign the next task +3. Check for idle agents (no message in >30min on assigned task) +4. Relance idle agents or reassign their tasks +``` + +## Examples + +### Example 1: Delegating a Code Task + +``` +[ORCHESTRATOR -> code-architect] TASK: Add rate limiting to /api/users +SCOPE: src/middleware/rate-limit.ts only +VERIFICATION: npm test -- --grep "rate-limit" +DEADLINE: 30 minutes +``` + +### Example 2: Handling a Duplicate + +``` +User asks: "Fix the login bug" +Registry check: Task #47 "Fix authentication bug" is IN_PROGRESS by security-reviewer +Decision: SKIP — similar task already assigned (78% match) +Action: Notify user of existing task, wait for completion +``` + +## Best Practices + +- Always define NOT-blocks for every agent (what they must refuse to do) +- Use SQLite for the task registry (lightweight, no server needed) +- Set similarity threshold at 55% for anti-duplication (lower = too many false positives) +- Require evidence-based quality gates (not just agent claims) +- Log every delegation with: task ID, agent, scope, deadline, verification command + +## Common Pitfalls + +- **Problem:** Orchestrator starts doing work instead of delegating + **Solution:** Add explicit NOT-blocks and role boundaries + +- **Problem:** Two agents modify the same file simultaneously + **Solution:** Task registry with file-level locking and queue system + +- **Problem:** Agent claims "done" without actual changes + **Solution:** Quality gate checks git diff before accepting completion + +- **Problem:** Tasks pile up without progress + **Solution:** 30-minute heartbeat catches stale assignments and reassigns + +## Related Skills + +- `@code-review` - For reviewing code changes after delegation +- `@test-driven-development` - For ensuring quality in agent output +- `@project-management` - For tracking multi-agent project progress diff --git a/skills_index.json b/skills_index.json index 14005a20..b3485bae 100644 --- a/skills_index.json +++ b/skills_index.json @@ -18653,6 +18653,28 @@ "reasons": [] } }, + { + "id": "multi-agent-task-orchestrator", + "path": "skills/multi-agent-task-orchestrator", + "category": "agent-orchestration", + "name": "multi-agent-task-orchestrator", + "description": "Route tasks to specialized AI agents with anti-duplication, quality gates, and 30-minute heartbeat monitoring", + "risk": "safe", + "source": "community", + "date_added": "2026-04-09", + "plugin": { + "targets": { + "codex": "supported", + "claude": "supported" + }, + "setup": { + "type": "none", + "summary": "", + "docs": null + }, + "reasons": [] + } + }, { "id": "multi-cloud-architecture", "path": "skills/multi-cloud-architecture",