firefrost-gaming/skill-seekers-reference
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update all documentation for 17 source types

Browse Source 
Update 32 documentation files across English and Chinese (zh-CN) docs
to reflect the 10 new source types added in the previous commit.

Updated files:
- README.md, README.zh-CN.md — taglines, feature lists, examples, install extras
- docs/reference/ — CLI_REFERENCE, FEATURE_MATRIX, MCP_REFERENCE, CONFIG_FORMAT, API_REFERENCE
- docs/features/ — UNIFIED_SCRAPING with generic merge docs
- docs/advanced/ — multi-source guide, MCP server guide
- docs/getting-started/ — installation extras, quick-start examples
- docs/user-guide/ — core-concepts, scraping, packaging, workflows (complex-merge)
- docs/ — FAQ, TROUBLESHOOTING, BEST_PRACTICES, ARCHITECTURE, UNIFIED_PARSERS, README
- Root — BULLETPROOF_QUICKSTART, CONTRIBUTING, ROADMAP
- docs/zh-CN/ — Chinese translations for all of the above

32 files changed, +3,016 lines, -245 lines
This commit is contained in:
yusyus
2026-03-15 15:56:04 +03:00
parent 53b911b697
commit 37cb307455
32 changed files with 3011 additions and 240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
docs/reference/API_REFERENCE.md
View File

@@ -1,7 +1,7 @@
# API Reference - Programmatic Usage
**Version:** 3.1.0-dev
**Last Updated:** 2026-02-18
**Version:** 3.2.0
**Last Updated:** 2026-03-15
**Status:** ✅ Production Ready
---
@@ -217,7 +217,7 @@ skill_path = scrape_pdf(
### 4. Unified Multi-Source Scraping API
Combine multiple sources (docs + GitHub + PDF) into a single unified skill.
Combine multiple sources (any of 17 supported types) into a single unified skill.
#### Unified Scraping
@@ -552,27 +552,47 @@ Skill Seekers uses JSON configuration files to define scraping behavior.
### Unified Config Schema (Multi-Source)
Supports all 17 source types: `documentation`, `github`, `pdf`, `local`, `word`, `video`, `epub`, `jupyter`, `html`, `openapi`, `asciidoc`, `pptx`, `rss`, `manpage`, `confluence`, `notion`, `chat`.
```json
{
"name": "framework-unified",
"description": "Complete framework documentation",
"sources": {
"documentation": {
"type": "docs",
"merge_mode": "rule-based",
"sources": [
{
"type": "documentation",
"base_url": "https://docs.example.com/",
"selectors": { "main_content": "article" }
},
"github": {
{
"type": "github",
"repo_url": "https://github.com/org/repo",
"analysis_depth": "c3x"
"repo": "org/repo",
"include_code": true,
"code_analysis_depth": "deep"
},
"pdf": {
{
"type": "pdf",
"pdf_path": "manual.pdf",
"enable_ocr": true
"path": "manual.pdf"
},
{
"type": "openapi",
"path": "specs/openapi.yaml"
},
{
"type": "video",
"url": "https://www.youtube.com/watch?v=example"
},
{
"type": "jupyter",
"path": "notebooks/examples.ipynb"
},
{
"type": "confluence",
"base_url": "https://company.atlassian.net/wiki",
"space_key": "DOCS"
}
},
],
"conflict_resolution": "prefer_code",
"merge_strategy": "smart"
}
@@ -961,7 +981,21 @@ monitor_enhancement('output/react/', watch=True)
| **Documentation Scraping** | `doc_scraper` | Extract from docs websites |
| **GitHub Analysis** | `github_scraper` | Analyze code repositories |
| **PDF Extraction** | `pdf_scraper` | Extract from PDF files |
| **Unified Scraping** | `unified_scraper` | Multi-source scraping |
| **Word Extraction** | `word_scraper` | Extract from .docx files |
| **EPUB Extraction** | `epub_scraper` | Extract from .epub files |
| **Video Transcription** | `video_scraper` | Extract from YouTube/Vimeo/local videos |
| **Jupyter Extraction** | `jupyter_scraper` | Extract from .ipynb notebooks |
| **HTML Extraction** | `html_scraper` | Extract from local HTML files |
| **OpenAPI Parsing** | `openapi_scraper` | Parse OpenAPI/Swagger specs |
| **AsciiDoc Extraction** | `asciidoc_scraper` | Extract from .adoc files |
| **PowerPoint Extraction** | `pptx_scraper` | Extract from .pptx files |
| **RSS/Atom Extraction** | `rss_scraper` | Extract from RSS/Atom feeds |
| **Man Page Extraction** | `manpage_scraper` | Extract from Unix man pages |
| **Confluence Extraction** | `confluence_scraper` | Extract from Confluence wikis |
| **Notion Extraction** | `notion_scraper` | Extract from Notion workspaces |
| **Chat Extraction** | `chat_scraper` | Extract from Slack/Discord exports |
| **Local Codebase Analysis** | `codebase_scraper` | Analyze local directories |
| **Unified Scraping** | `unified_scraper` | Multi-source scraping (17 types) |
| **Skill Packaging** | `adaptors` | Package for LLM platforms |
| **Skill Upload** | `adaptors` | Upload to platforms |
| **AI Enhancement** | `adaptors` | Improve skill quality |
@@ -979,6 +1013,6 @@ monitor_enhancement('output/react/', watch=True)
---
**Version:** 3.1.0-dev
**Last Updated:** 2026-02-18
**Version:** 3.2.0
**Last Updated:** 2026-03-15
**Status:** ✅ Production Ready

368
docs/reference/CLI_REFERENCE.md
View File

@@ -1,8 +1,8 @@
# CLI Reference - Skill Seekers
> **Version:** 3.1.2
> **Last Updated:** 2026-02-23
> **Complete reference for all 20 CLI commands**
> **Version:** 3.2.0
> **Last Updated:** 2026-03-15
> **Complete reference for all 30 CLI commands**
---
@@ -14,19 +14,29 @@
- [Environment Variables](#environment-variables)
- [Command Reference](#command-reference)
- [analyze](#analyze) - Analyze local codebase
- [asciidoc](#asciidoc) - Extract from AsciiDoc files
- [chat](#chat) - Extract from Slack/Discord
- [config](#config) - Configuration wizard
- [confluence](#confluence) - Extract from Confluence
- [create](#create) - Create skill (auto-detects source)
- [enhance](#enhance) - AI enhancement (local mode)
- [enhance-status](#enhance-status) - Monitor enhancement
- [estimate](#estimate) - Estimate page counts
- [github](#github) - Scrape GitHub repository
- [html](#html) - Extract from local HTML files
- [install](#install) - One-command complete workflow
- [install-agent](#install-agent) - Install to AI agent
- [jupyter](#jupyter) - Extract from Jupyter notebooks
- [manpage](#manpage) - Extract from man pages
- [multilang](#multilang) - Multi-language docs
- [notion](#notion) - Extract from Notion
- [openapi](#openapi) - Extract from OpenAPI/Swagger specs
- [package](#package) - Package skill for platform
- [pdf](#pdf) - Extract from PDF
- [pptx](#pptx) - Extract from PowerPoint files
- [quality](#quality) - Quality scoring
- [resume](#resume) - Resume interrupted jobs
- [rss](#rss) - Extract from RSS/Atom feeds
- [scrape](#scrape) - Scrape documentation
- [stream](#stream) - Stream large files
- [unified](#unified) - Multi-source scraping
@@ -42,7 +52,7 @@
## Overview
Skill Seekers provides a unified CLI for converting documentation, GitHub repositories, PDFs, and local codebases into AI-ready skills.
Skill Seekers provides a unified CLI for converting documentation, GitHub repositories, PDFs, videos, notebooks, wikis, and 17 total source types into AI-ready skills for 16+ LLM platforms and RAG pipelines.
### Installation
@@ -172,6 +182,74 @@ skill-seekers analyze --directory ./my-project --skip-dependency-graph --skip-pa
---
### asciidoc
Extract content from AsciiDoc files and generate skill.
**Purpose:** Convert `.adoc` / `.asciidoc` documentation into AI-ready skills.
**Syntax:**
```bash
skill-seekers asciidoc [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--asciidoc-path PATH` | Path to AsciiDoc file or directory |
| `-n, --name` | Skill name |
| `--from-json FILE` | Build from extracted JSON |
| `--enhance-level` | AI enhancement (default: 0) |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# Single file
skill-seekers asciidoc --asciidoc-path guide.adoc --name my-guide
# Directory of AsciiDoc files
skill-seekers asciidoc --asciidoc-path ./docs/ --name project-docs
```
---
### chat
Extract knowledge from Slack or Discord chat exports.
**Purpose:** Convert chat history into searchable AI-ready skills.
**Syntax:**
```bash
skill-seekers chat [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--export-path PATH` | Path to chat export directory or file |
| `--platform {slack,discord}` | Chat platform (default: slack) |
| `--token TOKEN` | API token for authentication |
| `--channel CHANNEL` | Channel name or ID to extract from |
| `--max-messages N` | Max messages to extract (default: 10000) |
| `-n, --name` | Skill name |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# From Slack export
skill-seekers chat --export-path ./slack-export/ --name team-knowledge
# From Discord via API
skill-seekers chat --platform discord --token $DISCORD_TOKEN --channel general --name discord-docs
```
---
### config
Interactive configuration wizard for API keys and settings.
@@ -210,6 +288,43 @@ skill-seekers config --test
---
### confluence
Extract content from Confluence wikis.
**Purpose:** Convert Confluence spaces into AI-ready skills via API or HTML export.
**Syntax:**
```bash
skill-seekers confluence [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--base-url URL` | Confluence instance base URL |
| `--space-key KEY` | Confluence space key |
| `--export-path PATH` | Path to Confluence HTML/XML export directory |
| `--username USER` | Confluence username |
| `--token TOKEN` | Confluence API token |
| `--max-pages N` | Max pages to extract (default: 500) |
| `-n, --name` | Skill name |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# Via API
skill-seekers confluence --base-url https://wiki.example.com --space-key DEV \
--username user@example.com --token $CONFLUENCE_TOKEN --name dev-wiki
# From export
skill-seekers confluence --export-path ./confluence-export/ --name team-docs
```
---
### create
Create skill from any source. Auto-detects source type.
@@ -234,6 +349,15 @@ skill-seekers create [source] [options]
| `owner/repo` | GitHub | `facebook/react` |
| `./path` | Local codebase | `./my-project` |
| `*.pdf` | PDF | `manual.pdf` |
| `*.docx` | Word | `report.docx` |
| `*.epub` | EPUB | `book.epub` |
| `*.ipynb` | Jupyter Notebook | `analysis.ipynb` |
| `*.html`/`*.htm` | Local HTML | `docs.html` |
| `*.yaml`/`*.yml` | OpenAPI/Swagger | `openapi.yaml` |
| `*.adoc`/`*.asciidoc` | AsciiDoc | `guide.adoc` |
| `*.pptx` | PowerPoint | `slides.pptx` |
| `*.rss`/`*.atom` | RSS/Atom feed | `feed.rss` |
| `*.1`-`*.8`/`*.man` | Man page | `grep.1` |
| `*.json` | Config file | `config.json` |
**Flags:**
@@ -473,6 +597,39 @@ skill-seekers github --repo facebook/react --scrape-only
---
### html
Extract content from local HTML files and generate skill.
**Purpose:** Convert local HTML documentation into AI-ready skills (for offline/exported docs).
**Syntax:**
```bash
skill-seekers html [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--html-path PATH` | Path to HTML file or directory |
| `-n, --name` | Skill name |
| `--from-json FILE` | Build from extracted JSON |
| `--enhance-level` | AI enhancement (default: 0) |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# Single HTML file
skill-seekers html --html-path docs/index.html --name my-docs
# Directory of HTML files
skill-seekers html --html-path ./html-export/ --name exported-docs
```
---
### install
One-command complete workflow: fetch → scrape → enhance → package → upload.
@@ -558,6 +715,72 @@ skill-seekers install-agent output/react/ --agent cursor --force
---
### jupyter
Extract content from Jupyter Notebook files and generate skill.
**Purpose:** Convert `.ipynb` notebooks into AI-ready skills with code, markdown, and outputs.
**Syntax:**
```bash
skill-seekers jupyter [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--notebook PATH` | Path to .ipynb file or directory |
| `-n, --name` | Skill name |
| `--from-json FILE` | Build from extracted JSON |
| `--enhance-level` | AI enhancement (default: 0) |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# Single notebook
skill-seekers jupyter --notebook analysis.ipynb --name data-analysis
# Directory of notebooks
skill-seekers jupyter --notebook ./notebooks/ --name ml-tutorials
```
---
### manpage
Extract content from Unix/Linux man pages and generate skill.
**Purpose:** Convert man pages into AI-ready reference skills.
**Syntax:**
```bash
skill-seekers manpage [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--man-names NAMES` | Comma-separated man page names (e.g., `ls,grep,find`) |
| `--man-path PATH` | Path to directory containing man page files |
| `--sections SECTIONS` | Comma-separated section numbers (e.g., `1,3,8`) |
| `-n, --name` | Skill name |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# By name (system man pages)
skill-seekers manpage --man-names ls,grep,find,awk --name unix-essentials
# From directory
skill-seekers manpage --man-path /usr/share/man/man1/ --sections 1 --name section1-cmds
```
---
### multilang
Multi-language documentation support.
@@ -590,6 +813,75 @@ skill-seekers multilang --config configs/docs.json --languages en,zh,es
---
### notion
Extract content from Notion workspaces.
**Purpose:** Convert Notion pages and databases into AI-ready skills via API or export.
**Syntax:**
```bash
skill-seekers notion [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--database-id ID` | Notion database ID to extract from |
| `--page-id ID` | Notion page ID to extract from |
| `--export-path PATH` | Path to Notion export directory |
| `--token TOKEN` | Notion integration token |
| `--max-pages N` | Max pages to extract (default: 500) |
| `-n, --name` | Skill name |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# Via API
skill-seekers notion --database-id abc123 --token $NOTION_TOKEN --name team-docs
# From export
skill-seekers notion --export-path ./notion-export/ --name project-wiki
```
---
### openapi
Extract content from OpenAPI/Swagger specifications and generate skill.
**Purpose:** Convert API specs into AI-ready reference skills with endpoint documentation.
**Syntax:**
```bash
skill-seekers openapi [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--spec PATH` | Path to OpenAPI/Swagger spec file |
| `--spec-url URL` | URL to OpenAPI/Swagger spec |
| `-n, --name` | Skill name |
| `--from-json FILE` | Build from extracted JSON |
| `--enhance-level` | AI enhancement (default: 0) |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# From local file
skill-seekers openapi --spec api/openapi.yaml --name my-api
# From URL
skill-seekers openapi --spec-url https://petstore.swagger.io/v2/swagger.json --name petstore
```
---
### package
Package skill directory into platform-specific format.
@@ -713,6 +1005,39 @@ skill-seekers pdf --pdf manual.pdf --name test --dry-run
---
### pptx
Extract content from PowerPoint files and generate skill.
**Purpose:** Convert `.pptx` presentations into AI-ready skills.
**Syntax:**
```bash
skill-seekers pptx [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--pptx PATH` | Path to PowerPoint file (.pptx) |
| `-n, --name` | Skill name |
| `--from-json FILE` | Build from extracted JSON |
| `--enhance-level` | AI enhancement (default: 0) |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# Extract from presentation
skill-seekers pptx --pptx training-slides.pptx --name training-material
# With enhancement
skill-seekers pptx --pptx architecture.pptx --name arch-overview --enhance-level 2
```
---
### quality
Analyze and score skill documentation quality.
@@ -791,6 +1116,41 @@ skill-seekers resume --clean
---
### rss
Extract content from RSS/Atom feeds and generate skill.
**Purpose:** Convert blog feeds and news sources into AI-ready skills.
**Syntax:**
```bash
skill-seekers rss [options]
```
**Key Flags:**
| Flag | Description |
|------|-------------|
| `--feed-url URL` | URL of the RSS/Atom feed |
| `--feed-path PATH` | Path to local RSS/Atom feed file |
| `--follow-links` | Follow article links for full content (default: true) |
| `--no-follow-links` | Use feed summary only |
| `--max-articles N` | Max articles to extract (default: 50) |
| `-n, --name` | Skill name |
| `--dry-run` | Preview without executing |
**Examples:**
```bash
# From URL
skill-seekers rss --feed-url https://blog.example.com/feed.xml --name blog-knowledge
# From local file, summaries only
skill-seekers rss --feed-path ./feed.rss --no-follow-links --name feed-summaries
```
---
### scrape
Scrape documentation website and generate skill.

214
docs/reference/CONFIG_FORMAT.md
View File

@@ -1,8 +1,8 @@
# Config Format Reference - Skill Seekers
> **Version:** 3.1.4
> **Last Updated:** 2026-02-26
> **Complete JSON configuration specification**
> **Version:** 3.2.0
> **Last Updated:** 2026-03-15
> **Complete JSON configuration specification for 17 source types**
---
@@ -14,6 +14,7 @@
- [GitHub Source](#github-source)
- [PDF Source](#pdf-source)
- [Local Source](#local-source)
- [Additional Source Types](#additional-source-types)
- [Unified (Multi-Source) Config](#unified-multi-source-config)
- [Common Fields](#common-fields)
- [Selectors](#selectors)
@@ -266,6 +267,158 @@ For analyzing local codebases.
---
### Additional Source Types
The following 10 source types were added in v3.2.0. Each can be used as a standalone config or within a unified `sources` array.
#### Jupyter Notebook Source
```json
{
"name": "ml-tutorial",
"sources": [{
"type": "jupyter",
"notebook_path": "notebooks/tutorial.ipynb"
}]
}
```
#### Local HTML Source
```json
{
"name": "offline-docs",
"sources": [{
"type": "html",
"html_path": "./exported-docs/"
}]
}
```
#### OpenAPI/Swagger Source
```json
{
"name": "petstore-api",
"sources": [{
"type": "openapi",
"spec_path": "api/openapi.yaml",
"spec_url": "https://petstore.swagger.io/v2/swagger.json"
}]
}
```
#### AsciiDoc Source
```json
{
"name": "project-guide",
"sources": [{
"type": "asciidoc",
"asciidoc_path": "./docs/guide.adoc"
}]
}
```
#### PowerPoint Source
```json
{
"name": "training-slides",
"sources": [{
"type": "pptx",
"pptx_path": "presentations/training.pptx"
}]
}
```
#### RSS/Atom Feed Source
```json
{
"name": "engineering-blog",
"sources": [{
"type": "rss",
"feed_url": "https://engineering.example.com/feed.xml",
"follow_links": true,
"max_articles": 50
}]
}
```
#### Man Page Source
```json
{
"name": "unix-tools",
"sources": [{
"type": "manpage",
"man_names": "ls,grep,find,awk,sed",
"sections": "1,3"
}]
}
```
#### Confluence Source
```json
{
"name": "team-wiki",
"sources": [{
"type": "confluence",
"base_url": "https://wiki.example.com",
"space_key": "DEV",
"username": "user@example.com",
"max_pages": 500
}]
}
```
#### Notion Source
```json
{
"name": "product-docs",
"sources": [{
"type": "notion",
"database_id": "abc123def456",
"max_pages": 500
}]
}
```
#### Chat (Slack/Discord) Source
```json
{
"name": "team-knowledge",
"sources": [{
"type": "chat",
"export_path": "./slack-export/",
"platform": "slack",
"channel": "engineering",
"max_messages": 10000
}]
}
```
#### Additional Source Fields Reference
| Source Type | Required Fields | Optional Fields |
|-------------|-----------------|-----------------|
| `jupyter` | `notebook_path` | — |
| `html` | `html_path` | — |
| `openapi` | `spec_path` or `spec_url` | — |
| `asciidoc` | `asciidoc_path` | — |
| `pptx` | `pptx_path` | — |
| `rss` | `feed_url` or `feed_path` | `follow_links`, `max_articles` |
| `manpage` | `man_names` or `man_path` | `sections` |
| `confluence` | `base_url` + `space_key` or `export_path` | `username`, `token`, `max_pages` |
| `notion` | `database_id` or `page_id` or `export_path` | `token`, `max_pages` |
| `chat` | `export_path` | `platform`, `token`, `channel`, `max_messages` |
---
## Unified (Multi-Source) Config
Combine multiple sources into one skill with conflict detection.
@@ -380,14 +533,27 @@ Unified configs support defining enhancement workflows at the top level:
#### Source Types in Unified Config
Each source in the `sources` array can be:
Each source in the `sources` array can be any of the 17 supported types:
| Type | Required Fields |
|------|-----------------|
| `docs` | `base_url` |
| `documentation` / `docs` | `base_url` |
| `github` | `repo` |
| `pdf` | `pdf_path` |
| `word` | `docx_path` |
| `epub` | `epub_path` |
| `video` | `url` or `video_path` |
| `local` | `directory` |
| `jupyter` | `notebook_path` |
| `html` | `html_path` |
| `openapi` | `spec_path` or `spec_url` |
| `asciidoc` | `asciidoc_path` |
| `pptx` | `pptx_path` |
| `rss` | `feed_url` or `feed_path` |
| `manpage` | `man_names` or `man_path` |
| `confluence` | `base_url` + `space_key` or `export_path` |
| `notion` | `database_id` or `page_id` or `export_path` |
| `chat` | `export_path` |
---
@@ -606,6 +772,44 @@ Control which URLs are included or excluded:
}
```
### Unified with New Source Types
```json
{
"name": "project-complete",
"description": "Full project knowledge from multiple source types",
"merge_mode": "claude-enhanced",
"sources": [
{
"type": "docs",
"name": "project-docs",
"base_url": "https://docs.example.com/",
"max_pages": 200
},
{
"type": "github",
"name": "project-code",
"repo": "example/project"
},
{
"type": "openapi",
"name": "project-api",
"spec_path": "api/openapi.yaml"
},
{
"type": "confluence",
"name": "project-wiki",
"export_path": "./confluence-export/"
},
{
"type": "jupyter",
"name": "project-notebooks",
"notebook_path": "./notebooks/"
}
]
}
```
### Local Project
```json

83
docs/reference/FEATURE_MATRIX.md
View File

@@ -13,28 +13,55 @@ Complete feature support across all platforms and skill modes.
## Skill Mode Support
| Mode | Description | Platforms | Example Configs |
|------|-------------|-----------|-----------------|
| **Documentation** | Scrape HTML docs | All 4 | react.json, django.json (14 total) |
| **GitHub** | Analyze repositories | All 4 | react_github.json, godot_github.json |
| **PDF** | Extract from PDFs | All 4 | example_pdf.json |
| **Unified** | Multi-source (docs+GitHub+PDF) | All 4 | react_unified.json (5 total) |
| **Local Repo** | Unlimited local analysis | All 4 | deck_deck_go_local.json |
| Mode | Description | Platforms | CLI Command | `create` Detection |
|------|-------------|-----------|-------------|-------------------|
| **Documentation** | Scrape HTML docs | All 4 | `scrape` | `https://...` URLs |
| **GitHub** | Analyze repositories | All 4 | `github` | `owner/repo` or github.com URLs |
| **PDF** | Extract from PDFs | All 4 | `pdf` | `.pdf` extension |
| **Word** | Extract from DOCX | All 4 | `word` | `.docx` extension |
| **EPUB** | Extract from EPUB | All 4 | `epub` | `.epub` extension |
| **Video** | Video transcription | All 4 | `video` | YouTube/Vimeo URLs, video extensions |
| **Local Repo** | Local codebase analysis | All 4 | `analyze` | Directory paths |
| **Jupyter** | Extract from notebooks | All 4 | `jupyter` | `.ipynb` extension |
| **HTML** | Extract local HTML files | All 4 | `html` | `.html`/`.htm` extension |
| **OpenAPI** | Extract API specs | All 4 | `openapi` | `.yaml`/`.yml` with OpenAPI content |
| **AsciiDoc** | Extract AsciiDoc files | All 4 | `asciidoc` | `.adoc`/`.asciidoc` extension |
| **PowerPoint** | Extract from PPTX | All 4 | `pptx` | `.pptx` extension |
| **RSS/Atom** | Extract from feeds | All 4 | `rss` | `.rss`/`.atom` extension |
| **Man Pages** | Extract man pages | All 4 | `manpage` | `.1`-`.8`/`.man` extension |
| **Confluence** | Extract from Confluence | All 4 | `confluence` | API or export directory |
| **Notion** | Extract from Notion | All 4 | `notion` | API or export directory |
| **Chat** | Extract Slack/Discord | All 4 | `chat` | Export directory or API |
| **Unified** | Multi-source combination | All 4 | `unified` | N/A (config-driven) |
## CLI Command Support
| Command | Platforms | Skill Modes | Multi-Platform Flag |
|---------|-----------|-------------|---------------------|
| `scrape` | All | Docs only | No (output is universal) |
| `github` | All | GitHub only | No (output is universal) |
| `pdf` | All | PDF only | No (output is universal) |
| `unified` | All | Unified only | No (output is universal) |
| `enhance` | Claude, Gemini, OpenAI | All | ✅ `--target` |
| `package` | All | All | ✅ `--target` |
| `upload` | Claude, Gemini, OpenAI | All | ✅ `--target` |
| `estimate` | All | Docs only | No (estimation is universal) |
| `install` | All | All | ✅ `--target` |
| `install-agent` | All | All | No (agent-specific paths) |
| Command | Platforms | Skill Modes | Multi-Platform Flag | Optional Deps |
|---------|-----------|-------------|---------------------|---------------|
| `scrape` | All | Docs only | No (output is universal) | None |
| `github` | All | GitHub only | No (output is universal) | None |
| `pdf` | All | PDF only | No (output is universal) | `[pdf]` |
| `word` | All | Word only | No (output is universal) | `[word]` |
| `epub` | All | EPUB only | No (output is universal) | `[epub]` |
| `video` | All | Video only | No (output is universal) | `[video]` |
| `analyze` | All | Local only | No (output is universal) | None |
| `jupyter` | All | Jupyter only | No (output is universal) | `[jupyter]` |
| `html` | All | HTML only | No (output is universal) | None |
| `openapi` | All | OpenAPI only | No (output is universal) | `[openapi]` |
| `asciidoc` | All | AsciiDoc only | No (output is universal) | `[asciidoc]` |
| `pptx` | All | PPTX only | No (output is universal) | `[pptx]` |
| `rss` | All | RSS only | No (output is universal) | `[rss]` |
| `manpage` | All | Man pages only | No (output is universal) | None |
| `confluence` | All | Confluence only | No (output is universal) | `[confluence]` |
| `notion` | All | Notion only | No (output is universal) | `[notion]` |
| `chat` | All | Chat only | No (output is universal) | `[chat]` |
| `unified` | All | Unified only | No (output is universal) | Varies by source |
| `enhance` | Claude, Gemini, OpenAI | All | ✅ `--target` | None |
| `package` | All | All | ✅ `--target` | None |
| `upload` | Claude, Gemini, OpenAI | All | ✅ `--target` | None |
| `estimate` | All | Docs only | No (estimation is universal) | None |
| `install` | All | All | ✅ `--target` | None |
| `install-agent` | All | All | No (agent-specific paths) | None |
## MCP Tool Support
@@ -50,6 +77,7 @@ Complete feature support across all platforms and skill modes.
| `scrape_docs` | All | Docs + Unified | No (output is universal) |
| `scrape_github` | All | GitHub only | No (output is universal) |
| `scrape_pdf` | All | PDF only | No (output is universal) |
| `scrape_generic` | All | 10 new types | No (output is universal) |
| **Packaging Tools** |
| `package_skill` | All | All | ✅ `target` parameter |
| `upload_skill` | Claude, Gemini, OpenAI | All | ✅ `target` parameter |
@@ -260,8 +288,21 @@ Before release, verify all combinations:
- [ ] Docs → Markdown
- [ ] GitHub → All platforms
- [ ] PDF → All platforms
- [ ] Unified → All platforms
- [ ] Word → All platforms
- [ ] EPUB → All platforms
- [ ] Video → All platforms
- [ ] Local Repo → All platforms
- [ ] Jupyter → All platforms
- [ ] HTML → All platforms
- [ ] OpenAPI → All platforms
- [ ] AsciiDoc → All platforms
- [ ] PPTX → All platforms
- [ ] RSS → All platforms
- [ ] Man Pages → All platforms
- [ ] Confluence → All platforms
- [ ] Notion → All platforms
- [ ] Chat → All platforms
- [ ] Unified → All platforms
## Platform-Specific Notes
@@ -310,7 +351,7 @@ A: Yes! Enhancement adds platform-specific formatting:
- OpenAI: Plain text assistant instructions
**Q: Do all skill modes work with all platforms?**
A: Yes! All 5 skill modes (Docs, GitHub, PDF, Unified, Local Repo) work with all 4 platforms.
A: Yes! All 17 source types work with all 4 platforms (Claude, Gemini, OpenAI, Markdown).
## See Also

82
docs/reference/MCP_REFERENCE.md
View File

@@ -1,8 +1,8 @@
# MCP Reference - Skill Seekers
> **Version:** 3.1.0
> **Last Updated:** 2026-02-16
> **Complete reference for 26 MCP tools**
> **Version:** 3.2.0
> **Last Updated:** 2026-03-15
> **Complete reference for 27 MCP tools**
---
@@ -79,7 +79,7 @@ Essential tools for basic skill creation workflow:
| `enhance_skill` | AI enhancement |
| `install_skill` | Complete workflow |
### Extended Tools (9)
### Extended Tools (10)
Advanced scraping and analysis tools:
@@ -88,6 +88,7 @@ Advanced scraping and analysis tools:
| `scrape_github` | GitHub repository analysis |
| `scrape_pdf` | PDF extraction |
| `scrape_codebase` | Local codebase analysis |
| `scrape_generic` | Generic scraper for 10 new source types |
| `unified_scrape` | Multi-source scraping |
| `detect_patterns` | Pattern detection |
| `extract_test_examples` | Extract usage examples from tests |
@@ -642,6 +643,65 @@ Find discrepancies between documentation and code.
---
#### scrape_generic
Scrape content from any of the 10 new source types.
**Purpose:** A generic entry point that delegates to the appropriate CLI scraper module for: jupyter, html, openapi, asciidoc, pptx, confluence, notion, rss, manpage, chat.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| `source_type` | string | Yes | One of: `jupyter`, `html`, `openapi`, `asciidoc`, `pptx`, `confluence`, `notion`, `rss`, `manpage`, `chat` |
| `name` | string | Yes | Skill name for the output |
| `path` | string | No | File or directory path (for file-based sources) |
| `url` | string | No | URL (for URL-based sources like confluence, notion, rss) |
**Note:** Either `path` or `url` must be provided depending on the source type.
**Source Type → Input Mapping:**
| Source Type | Typical Input | CLI Flag Used |
|-------------|--------------|---------------|
| `jupyter` | `path` | `--notebook` |
| `html` | `path` | `--html-path` |
| `openapi` | `path` | `--spec` |
| `asciidoc` | `path` | `--asciidoc-path` |
| `pptx` | `path` | `--pptx` |
| `manpage` | `path` | `--man-path` |
| `confluence` | `path` or `url` | `--export-path` / `--base-url` |
| `notion` | `path` or `url` | `--export-path` / `--database-id` |
| `rss` | `path` or `url` | `--feed-path` / `--feed-url` |
| `chat` | `path` | `--export-path` |
**Returns:** Scraping results with file paths and statistics
```json
{
"skill_directory": "output/my-api/",
"source_type": "openapi",
"status": "success"
}
```
**Example:**
```python
# Natural language
"Scrape the OpenAPI spec at api/openapi.yaml"
"Extract content from my Jupyter notebook analysis.ipynb"
"Process the Confluence export in ./wiki-export/"
"Convert the PowerPoint slides.pptx into a skill"
# Explicit tool call
scrape_generic(source_type="openapi", name="my-api", path="api/openapi.yaml")
scrape_generic(source_type="jupyter", name="ml-tutorial", path="notebooks/tutorial.ipynb")
scrape_generic(source_type="rss", name="blog", url="https://blog.example.com/feed.xml")
scrape_generic(source_type="confluence", name="wiki", path="./confluence-export/")
```
---
### Config Source Tools
#### add_config_source
@@ -1030,7 +1090,19 @@ Tools: `list_workflows` → `unified_scrape` → `enhance_skill` → `package_sk
---
### Pattern 5: Vector Database Export
### Pattern 5: New Source Type Scraping
```python
# Natural language sequence:
"Scrape the OpenAPI spec at api/openapi.yaml"
"Package the output for Claude"
```
Tools: `scrape_generic` → `package_skill`
---
### Pattern 6: Vector Database Export
```python
# Natural language sequence: