Skip to content
Back to search

skill_seekers

SkillWorks with Claude CodeGitHub

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/yusufkaraaslan/skill_seekers with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/yusufkaraaslan/skill_seekers'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yusufkaraaslan--skill-seekers/badge.svg)](/listings/yusufkaraaslan--skill-seekers)

HTML

<a href="/listings/yusufkaraaslan--skill-seekers"><img src="/api/listings/yusufkaraaslan--skill-seekers/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

# 1. Install
pip install skill-seekers

# 2. Create a skill from any source
skill-seekers create https://docs.djangoproject.com/

# Optional: preview how a source will be detected without creating anything
skill-seekers detect https://docs.djangoproject.com/ --json

# 3. Package it for your AI platform
skill-seekers package output/django --target claude

You now have `output/django-claude.zip`, ready to use.

# Pick a different AI agent for enhancement (default: claude)
skill-seekers create https://docs.djangoproject.com/ --agent kimi
skill-seekers create https://docs.djangoproject.com/ --agent-cmd "my-custom-agent run"

🛰️ AI-driven project scan

Point `scan` at a project and an AI agent reads its manifests, README, Dockerfile/CI and sampled source imports — then emits one config per detected framework, plus a `<project>-codebase.json` for your own code:

skill-seekers scan ./my-react-app --out ./configs/scanned/
# → react.json, vite.json, tailwind.json, jest.json, my-react-app-codebase.json

skill-seekers create ./configs/scanned/react.json

If a detection has no existing preset, the AI generates a fresh config; on exit you can optionally publish it back to the [community registry](https://github.com/yusufkaraaslan/skill-seekers-configs).

All 18 source types

skill-seekers create facebook/react            # GitHub repository
skill-seekers create ./my-project              # Local codebase
skill-seekers create manual.pdf                # PDF
skill-seekers create report.docx               # Word
skill-seekers create book.epub                 # EPUB
skill-seekers create notebook.ipynb            # Jupyter
skill-seekers create openapi.yaml              # OpenAPI/Swagger
skill-seekers create presentation.pptx         # PowerPoint
skill-seekers create guide.adoc                # AsciiDoc
skill-seekers create page.html                 # Local HTML (or a whole dir)
skill-seekers create feed.rss                  # RSS/Atom
skill-seekers create curl.1                    # Man page

# Video (YouTube, Vimeo, or local — needs skill-seekers[video])
skill-seekers create --video-url https://www.youtube.com/watch?v=... --name mytutorial
skill-seekers create --setup                   # auto-install GPU-aware visual deps

skill-seekers create --space-key TEAM --name wiki               # Confluence
skill-seekers create --database-id ... --name docs              # Notion
skill-seekers create --chat-export-path ./slack-export --name team-chat  # Slack/Discord

See the [Scraping Guide](docs/user-guide/02-scraping.md) for every source type and its options.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 438 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <img src="docs/assets/logo.png" alt="Skill Seekers" width="200"/>
  3. </p>
  4. # Skill Seekers
  5. English | [简体中文](README.zh-CN.md) | [日本語](README.ja.md) | [한국어](README.ko.md) | [Español](README.es.md) | [Français](README.fr.md) | [Deutsch](README.de.md) | [Português](README.pt-BR.md) | [Türkçe](README.tr.md) | [العربية](README.ar.md) | [हिन्दी](README.hi.md) | [Русский](README.ru.md)
  6. [![Version](https://img.shields.io/badge/version-3.9.0-blue.svg)](https://github.com/yusufkaraaslan/Skill_Seekers/releases)
  7. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  8. [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
  9. [![MCP Integration](https://img.shields.io/badge/MCP-40-Tools-blue.svg)](https://modelcontextprotocol.io)
  10. [![Tested](https://img.shields.io/badge/Tests-3900%2B%20Passing-brightgreen.svg)](tests/)
  11. [![PyPI version](https://badge.fury.io/py/skill-seekers.svg)](https://pypi.org/project/skill-seekers/)
  12. [![PyPI - Downloads](https://img.shields.io/pypi/dm/skill-seekers.svg)](https://pypi.org/project/skill-seekers/)
  13. [![Website](https://img.shields.io/badge/Website-skillseekersweb.com-blue.svg)](https://skillseekersweb.com/)
  14. [![GitHub Repo stars](https://img.shields.io/github/stars/yusufkaraaslan/Skill_Seekers?style=social)](https://github.com/yusufkaraaslan/Skill_Seekers)
  15. [![PyPI Downloads](https://static.pepy.tech/personalized-badge/skill-seekers?period=total&units=INTERNATIONAL_SYSTEM&left_color=BLACK&right_color=GREEN&left_text=downloads)](https://pepy.tech/projects/skill-seekers)
  16. <a href="https://trendshift.io/repositories/18329" target="_blank"><img src="https://trendshift.io/api/badge/repositories/18329" alt="yusufkaraaslan%2FSkill_Seekers | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
  17. **🧠 The data layer for AI systems.** Skill Seekers turns documentation sites, GitHub repos, PDFs, videos, notebooks, wikis, and more — **18 source types** — into structured knowledge assets, ready to power AI Skills (Claude, Gemini, OpenAI), RAG pipelines (LangChain, LlamaIndex, Pinecone), and AI coding assistants (Cursor, Windsurf, Cline). Prepare once, export to **22 targets**.
  18. ## 💛 Sponsors
  19. <!-- SPONSORS:START -->
  20. ### Bronze Sponsors
  21. <p align="center">
  22. <a href="https://fluxionai.world/register?utm_source=github&utm_medium=sponsor&utm_campaign=skillseekers"><img src="docs/assets/sponsors/fluxion-ai.png" alt="Fluxion AI" width="100"></a><br/><sub><b>Sponsor — Bronze</b></sub>
  23. </p>
  24. <!-- SPONSORS:END -->
  25. **[Become a sponsor](SPONSORSHIP.md)** · [GitHub Sponsors](https://github.com/sponsors/yusufkaraaslan)
  26. ---
  27. ## 🚀 Quick Start
  28. ```bash
  29. # 1. Install
  30. pip install skill-seekers
  31. # 2. Create a skill from any source
  32. skill-seekers create https://docs.djangoproject.com/
  33. # Optional: preview how a source will be detected without creating anything
  34. skill-seekers detect https://docs.djangoproject.com/ --json
  35. # 3. Package it for your AI platform
  36. skill-seekers package output/django --target claude
  37. ```
  38. You now have `output/django-claude.zip`, ready to use.
  39. ```bash
  40. # Pick a different AI agent for enhancement (default: claude)
  41. skill-seekers create https://docs.djangoproject.com/ --agent kimi
  42. skill-seekers create https://docs.djangoproject.com/ --agent-cmd "my-custom-agent run"
  43. ```
  44. ### 🛰️ AI-driven project scan
  45. Point `scan` at a project and an AI agent reads its manifests, README, Dockerfile/CI and sampled source imports — then emits one config per detected framework, plus a `<project>-codebase.json` for your own code:
  46. ```bash
  47. skill-seekers scan ./my-react-app --out ./configs/scanned/
  48. # → react.json, vite.json, tailwind.json, jest.json, my-react-app-codebase.json
  49. skill-seekers create ./configs/scanned/react.json
  50. ```
  51. If a detection has no existing preset, the AI generates a fresh config; on exit you can optionally publish it back to the [community registry](https://github.com/yusufkaraaslan/skill-seekers-configs).
  52. ### All 18 source types
  53. ```bash
  54. skill-seekers create facebook/react # GitHub repository
  55. skill-seekers create ./my-project # Local codebase
  56. skill-seekers create manual.pdf # PDF
  57. skill-seekers create report.docx # Word
  58. skill-seekers create book.epub # EPUB
  59. skill-seekers create notebook.ipynb # Jupyter
  60. skill-seekers create openapi.yaml # OpenAPI/Swagger
  61. skill-seekers create presentation.pptx # PowerPoint
  62. skill-seekers create guide.adoc # AsciiDoc
  63. skill-seekers create page.html # Local HTML (or a whole dir)
  64. skill-seekers create feed.rss # RSS/Atom
  65. skill-seekers create curl.1 # Man page
  66. # Video (YouTube, Vimeo, or local — needs skill-seekers[video])
  67. skill-seekers create --video-url https://www.youtube.com/watch?v=... --name mytutorial
  68. skill-seekers create --setup # auto-install GPU-aware visual deps
  69. skill-seekers create --space-key TEAM --name wiki # Confluence
  70. skill-seekers create --database-id ... --name docs # Notion
  71. skill-seekers create --chat-export-path ./slack-export --name team-chat # Slack/Discord
  72. ```
  73. See the [Scraping Guide](docs/user-guide/02-scraping.md) for every source type and its options.
  74. ---
  75. ## 📦 Installation
  76. ```bash
  77. pip install skill-seekers # Core: scraping, GitHub, PDF, packaging
  78. pip install skill-seekers[all-llms] # + every LLM platform
  79. pip install skill-seekers[mcp] # + MCP server
  80. pip install skill-seekers[all] # Everything
  81. ```
  82. **Not sure what you need?** Run the wizard: `skill-seekers-setup`
  83. <details>
  84. <summary><b>All installation extras</b></summary>
  85. | Install | Adds |
  86. |---------|------|
  87. | `skill-seekers[gemini]` | Google Gemini support |
  88. | `skill-seekers[openai]` | OpenAI ChatGPT support |
  89. | `skill-seekers[all-llms]` | All LLM platforms |
  90. | `skill-seekers[mcp]` | MCP server for Claude Code, Cursor, etc. |
  91. | `skill-seekers[video]` | YouTube/Vimeo transcript & metadata extraction |
  92. | `skill-seekers[video-full]` | + Whisper transcription & visual frame extraction |
  93. | `skill-seekers[jupyter]` | Jupyter Notebook support |
  94. | `skill-seekers[pptx]` | PowerPoint support |
  95. | `skill-seekers[confluence]` | Confluence wiki support |
  96. | `skill-seekers[notion]` | Notion pages support |
  97. | `skill-seekers[rss]` | RSS/Atom feed support |
  98. | `skill-seekers[chat]` | Slack/Discord chat export support |
  99. | `skill-seekers[asciidoc]` | AsciiDoc support |
  100. | `skill-seekers[all]` | Everything |
  101. > **Video visual deps (GPU-aware):** after installing `skill-seekers[video-full]`, run `skill-seekers create --setup` to auto-detect your GPU and install the matching PyTorch variant + easyocr.
  102. </details>
  103. **Prerequisites:** Python 3.10+, Git. New here? → **[Bulletproof Quick Start](docs/getting-started/BULLETPROOF_QUICKSTART.md)** 🎯
  104. ---
  105. ## 📚 Documentation
  106. | I want to... | Read this |
  107. |--------------|-----------|
  108. | **Get started quickly** | [Quick Start](docs/getting-started/02-quick-start.md) — 3 commands to your first skill |
  109. | **Understand the concepts** | [Core Concepts](docs/user-guide/01-core-concepts.md) |
  110. | **Scrape sources** | [Scraping Guide](docs/user-guide/02-scraping.md) — all 18 source types |
  111. | **Enhance skills with AI** | [Enhancement Guide](docs/user-guide/03-enhancement.md) · [Enhancement Modes](docs/features/ENHANCEMENT_MODES.md) |
  112. | **Export skills** | [Packaging Guide](docs/user-guide/04-packaging.md) |
  113. | **Build workflows** | [Workflows](docs/user-guide/05-workflows.md) |
  114. | **Look up a command** | [CLI Reference](docs/reference/CLI_REFERENCE.md) — all 19 commands |
  115. | **Configure** | [Config Format](docs/reference/CONFIG_FORMAT.md) · [Environment Variables](docs/reference/ENVIRONMENT_VARIABLES.md) |
  116. | **Set up MCP** | [MCP Setup](docs/guides/MCP_SETUP.md) · [MCP Reference](docs/reference/MCP_REFERENCE.md) |
  117. | **Integrate with RAG / IDEs** | [LangChain](docs/integrations/LANGCHAIN.md) · [RAG Pipelines](docs/integrations/RAG_PIPELINES.md) · [Cursor](docs/integrations/CURSOR.md) · [Windsurf](docs/integrations/WINDSURF.md) · [Cline](docs/integrations/CLINE.md) |
  118. | **Handle huge doc sets** | [Large Documentation](docs/reference/LARGE_DOCUMENTATION.md) — 10K–40K+ pages |
  119. | **Understand the architecture** | [UML Architecture](docs/UML_ARCHITECTURE.md) — 14 diagrams |
  120. | **Fix a problem** | [Troubleshooting](docs/user-guide/06-troubleshooting.md) |
  121. **Complete documentation index:** [docs/README.md](docs/README.md)
  122. ---
  123. ## 🎯 What you get
  124. | Use case | Output | Powers |
  125. |----------|--------|--------|
  126. | **AI Skills** | Comprehensive `SKILL.md` + reference files | Claude Code, Gemini, GPT |
  127. | **RAG pipelines** | Chunked documents with rich metadata | LangChain, LlamaIndex, Haystack |
  128. | **Vector databases** | Pre-formatted data ready for upsert | Pinecone, Chroma, Weaviate, FAISS, Qdrant |
  129. | **AI coding assistants** | Context files your IDE AI reads automatically | Cursor, Windsurf, Cline, Continue.dev |
  130. ### Export targets (22)
  131. ```bash
  132. skill-seekers package output/react --target claude # → Claude Skill (ZIP + YAML)
  133. skill-seekers package output/react --target langchain # → LangChain Documents
  134. skill-seekers package output/react --target llama-index # → LlamaIndex TextNodes
  135. skill-seekers package output/react --target ibm-bob # → IBM Bob skill directory
  136. ```
  137. **LLM platforms (13):** `claude` · `gemini` · `openai` · `minimax` · `opencode` · `kimi` · `deepseek` · `qwen` · `openrouter` · `requesty` · `together` · `fireworks` · `markdown`
  138. **RAG & vector (8):** `langchain` · `llama-index` · `haystack` · `chroma` · `faiss` · `weaviate` · `qdrant` · `pinecone`
  139. **Other (2):** `atlas` · `ibm-bob`
  140. See the [Feature Matrix](docs/reference/FEATURE_MATRIX.md) for per-platform support details.
  141. ### Why it matters
  142. - ⚡ **99% faster** — days of manual data prep → 15–45 minutes
  143. - 🎯 **Real skill quality** — 500+ line `SKILL.md` files with examples, patterns, and guides
  144. - 📊 **RAG-ready chunks** — smart chunking preserves code blocks and context
  145. - 🔄 **Multi-source** — combine docs + GitHub + PDFs + videos into one knowledge asset
  146. - 🌐 **One prep, every target** — export to 22 targets without re-scraping
  147. - ✅ **Battle-tested** — 3,900+ tests, 68 workflow presets, production-ready
  148. ---
  149. ## ✨ Key capabilities
  150. <details>
  151. <summary><b>Documentation scraping</b> — SPA discovery, llms.txt, smart categorization</summary>
  152. Three-layer discovery for JavaScript SPA sites (`sitemap.xml` → `llms.txt` → headless browser rendering), automatic `llms.txt` detection (10× faster when present), smart topic categorization, and a lenient HTML parser fallback so broken markup still scrapes.
  153. → [Scraping Guide](docs/user-guide/02-scraping.md) · [llms.txt Support](docs/reference/LLMS_TXT_SUPPORT.md)
  154. </details>
  155. <details>
  156. <summary><b>GitHub & codebase analysis (C3.x)</b> — AST parsing, pattern detection, how-to guides</summary>
  157. Three-stream architecture: code analysis (AST, design patterns, tests), documentation (README, `docs/`, wiki), and community (issues, PRs, metadata). The C3.x pipeline adds 10 GoF pattern detectors across 9 languages, usage examples extracted from tests, AI-written how-to guides, config extraction, and architecture overviews.
  158. ```bash
  159. skill-seekers create ./my-project --preset quick # 1–2 min, surface level
  160. skill-seekers create ./my-project --preset standard # balanced (default)
  161. skill-seekers create ./my-project --preset comprehensive # deep, exhaustive
  162. ```
  163. → [Pattern Detection](docs/features/PATTERN_DETECTION.md) · [How-To Guides](docs/features/HOW_TO_GUIDES.md) · [Test Example Extraction](docs/features/TEST_EXAMPLE_EXTRACTION.md)
  164. </details>
  165. <details>
  166. <summary><b>AI enhancement</b> — API or local agents, 68 workflow presets</summary>
  167. Every AI call runs through one transport, in **API mode** (Anthropic, Google Gemini, OpenAI, Moonshot/Kimi, MiniMax) or **LOCAL mode** (Claude Code, Kimi Code, Codex, Copilot, OpenCode, custom agents — no API costs). Control depth with `--enhance-level 0-3` and pick an agent with `--agent`.
  168. → [Enhancement Guide](docs/user-guide/03-enhancement.md) · [Enhancement Modes](docs/features/ENHANCEMENT_MODES.md) · [Multi-Agent Setup](docs/guides/MULTI_AGENT_SETUP.md)
  169. </details>
  170. <details>
  171. <summary><b>Unified multi-source scraping</b> — combine many sources into one skill</summary>
  172. One config can pull documentation, GitHub, PDFs, videos, and more into a single knowledge asset, with conflict detection and pairwise synthesis across sources.
  173. → [Unified Scraping](docs/features/UNIFIED_SCRAPING.md)
  174. </details>
  175. <details>
  176. <summary><b>Search index inside the skill</b> — query before you read (opt-in)</summary>
  177. `skill-seekers create <source> --index` adds a stdlib-only `scripts/search.py` and a SQLite FTS5 index over the generated references, so an agent can find the right `file#anchor` before reading a large Markdown file wholesale. Off by default; the Markdown is untouched.
  178. → [Skill Search Index](docs/features/SKILL_SEARCH_INDEX.md)
  179. </details>
  180. <details>
  181. <summary><b>Video extraction</b> — transcripts, frames, on-screen code</summary>
  182. YouTube, Vimeo, and local files. Three-tier transcript fallback (subtitles → YouTube transcript API → local Whisper), plus optional visual extraction that OCRs on-screen code from sampled frames.
  183. → [Video Guide](docs/VIDEO_GUIDE.md)
  184. </details>
  185. <details>
  186. <summary><b>Quality, sync & scale</b></summary>
  187. Quality scoring with a gate (`skill-seekers quality output/react/ --threshold 7`) or JSON stdout (`skill-seekers quality output/react/ --json`), provisional English readability metrics (informational — they never affect the score), doc-change detection with scheduled re-scrapes and notifications, streaming ingestion for very large doc sets, and incremental updates.
  188. → [Large Documentation](docs/reference/LARGE_DOCUMENTATION.md) · [Code Quality](docs/reference/CODE_QUALITY.md)
  189. </details>
  190. ---
  191. ## 🔌 MCP Integration (40 tools)
  192. Skill Seekers ships an MCP server for Claude Code, Cursor, Windsurf, VS Code + Cline, and IntelliJ IDEA.
  193. ```bash
  194. # stdio mode (Claude Code, VS Code + Cline)
  195. python -m skill_seekers.mcp.server_fastmcp
  196. # HTTP mode (Cursor, Windsurf, IntelliJ)
  197. python -m skill_seekers.mcp.server_fastmcp --transport http --port 8765
  198. ```
  199. Then just ask your assistant: *"Package and upload the React skill."*
  200. → [MCP Setup](docs/guides/MCP_SETUP.md) · [MCP Reference](docs/reference/MCP_REFERENCE.md) · [HTTP Transport](docs/guides/HTTP_TRANSPORT.md)
  201. ---
  202. ## 🤖 Installing to AI agents
  203. Skills install automatically into **19 AI coding agents**:
  204. ```bash
  205. skill-seekers install-agent output/react/ --agent cursor
  206. skill-seekers install-agent output/react/ --agent all # every detected agent
  207. skill-seekers install-agent output/react/ --agent cursor --dry-run
  208. ```
  209. | Agent | Path | Scope |
  210. |-------|------|-------|
  211. | Claude Code | `~/.claude/skills/` | Global |
  212. | Cursor | `.cursor/skills/` | Project |
  213. | VS Code / Copilot | `.github/skills/` | Project |
  214. | Amp | `~/.amp/skills/` | Global |
  215. | Goose | `~/.config/goose/skills/` | Global |
  216. | OpenCode | `~/.opencode/skills/` | Global |
  217. | Letta | `~/.letta/skills/` | Global |
  218. | Aide | `~/.aide/skills/` | Global |
  219. | Windsurf | `~/.windsurf/skills/` | Global |
  220. | Neovate | `~/.neovate/skills/` | Global |
  221. | Roo Code | `.roo/skills/` | Project |
  222. | Cline | `.cline/skills/` | Project |
  223. | Aider | `~/.aider/skills/` | Global |
  224. | Bolt | `.bolt/skills/` | Project |
  225. | Kilo Code | `.kilo/skills/` | Project |
  226. | Continue | `~/.continue/skills/` | Global |
  227. | Kimi Code | `~/.kimi/skills/` | Global |
  228. | IBM Bob | `.bob/skills/` | Project |
  229. ### Uploading to Claude
  230. ```bash
  231. export ANTHROPIC_API_KEY=sk-ant-...
  232. skill-seekers package output/react/ --upload # package + upload
  233. skill-seekers upload output/react.zip # upload an existing zip
  234. ```
  235. No API key? Package it and upload `output/react.zip` manually at [claude.ai/skills](https://claude.ai/skills).
  236. → [Upload Guide](docs/guides/UPLOAD_GUIDE.md)
  237. ---
  238. ## ⚙️ How it works
  239. ```mermaid
  240. graph LR
  241. A[Documentation Website] --> B[Skill Seekers]
  242. B --> C[Scraper]
  243. B --> D[AI Enhancement]
  244. B --> E[Packager]
  245. C --> F[Organized References]
  246. D --> F
  247. F --> E
  248. E --> G[AI Skill .zip]
  249. G --> H[Upload to AI Platform]
  250. ```
  251. 1. **Scrape** — extract every page (checking `llms.txt` first)
  252. 2. **Categorize** — organize content into topics (API, guides, tutorials, …)
  253. 3. **Enhance** — AI writes a comprehensive `SKILL.md` with examples
  254. 4. **Package** — bundle into a platform-ready artifact
  255. 5. **Upload** — ship it to your AI platform (optional)
  256. ### Architecture
  257. **8 core modules + 5 utility modules** (~200 classes):
  258. | Module | Purpose |
  259. |--------|---------|
  260. | **CLICore** | Git-style command dispatcher, source auto-detection |
  261. | **Scrapers** | 18 source-type extractors on a shared build layer |
  262. | **Adaptors** | 22 output platform formats behind one `SkillAdaptor` ABC |
  263. | **Analysis** | C3.x codebase pipeline, 10 GoF pattern detectors |
  264. | **Enhancement** | AI improvement via a single `AgentClient` transport |
  265. | **Packaging** | Package, upload, and install skills |
  266. | **MCP** | FastMCP server (40 tools, 10 tool modules) |
  267. | **Sync** | Doc change detection and notification |
  268. → [UML Architecture](docs/UML_ARCHITECTURE.md) · [API Reference](docs/reference/API_REFERENCE.md) · [Skill Architecture](docs/reference/SKILL_ARCHITECTURE.md)
  269. ---
  270. ## 🆕 New in v3.9.0
  271. - **HTML parser fallback for broken markup** (#96) — severely malformed pages no longer scrape as empty; well-formed pages are byte-identical.
  272. - **Transient-failure retries** — the doc scraper (#97) and MCP `fetch_config` (#92) now retry connection blips and 5xx with backoff; 4xx still fails fast.
  273. - **Whisper transcription fallback** (#420) — local videos without subtitles finally get a real transcript.
  274. - **MiniMax image OCR + registry-driven multimodal providers** (#423) — providers declare their wire protocol and image capability; China-issued keys work against the right endpoint.
  275. - **Token-lean GitHub issue defaults** (#169) — GitHub skills no longer bundle full closed-issue history by default.
  276. - **Env-driven CORS across all three servers** (#422, #424) — no more wildcard origins with credentials.
  277. Full history: **[CHANGELOG.md](CHANGELOG.md)**
  278. ---
  279. ## 📈 Performance
  280. | Documentation size | Time | Output |
  281. |---|---|---|
  282. | Small (< 100 pages) | 5–10 min | ~2 MB |
  283. | Medium (100–500 pages) | 15–30 min | ~10 MB |
  284. | Large (500–2,000 pages) | 30–60 min | ~40 MB |
  285. | Huge (10K–40K+ pages) | Use `stream` | See [Large Documentation](docs/reference/LARGE_DOCUMENTATION.md) |
  286. ---
  287. ## 🐛 Troubleshooting
  288. ```bash
  289. skill-seekers doctor # diagnose installation & environment
  290. skill-seekers doctor --json # machine-readable diagnostics for CI and agents
  291. skill-seekers sync-config # detect config drift
  292. ```
  293. Common issues and fixes: **[Troubleshooting Guide](docs/user-guide/06-troubleshooting.md)** · [TROUBLESHOOTING.md](docs/TROUBLESHOOTING.md)
  294. ---
  295. ## 🤝 Contributing
  296. Contributions are welcome — see **[CONTRIBUTING.md](CONTRIBUTING.md)**.
  297. - 📋 **[Development Roadmap & Tasks](https://github.com/users/yusufkaraaslan/projects/2)** — pick any task
  298. - 💬 **[Discussions](https://github.com/yusufkaraaslan/Skill_Seekers/discussions)** — questions and ideas
  299. - 🐛 **[Issues](https://github.com/yusufkaraaslan/Skill_Seekers/issues)** — bugs and feature requests
  300. ---
  301. ## 📝 License
  302. MIT — see [LICENSE](LICENSE).
  303. ## 🔒 Security
  304. [![MseeP.ai Security Assessment Badge](https://mseep.net/pr/yusufkaraaslan-skill-seekers-badge.png)](https://mseep.ai/app/yusufkaraaslan-skill-seekers)
  305. ---
  306. ## 🌐 Ecosystem
  307. Skill Seekers is a multi-repo project:
  308. | Repository | Description | Links |
  309. |-----------|-------------|-------|
  310. | **[Skill_Seekers](https://github.com/yusufkaraaslan/Skill_Seekers)** | Core CLI & MCP server (this repo) | [PyPI](https://pypi.org/project/skill-seekers/) |
  311. | **[skillseekersweb](https://github.com/yusufkaraaslan/skillseekersweb)** | Website & documentation | [Live](https://skillseekersweb.com/) |
  312. | **[skill-seekers-configs](https://github.com/yusufkaraaslan/skill-seekers-configs)** | Community config repository | |
  313. | **[skill-seekers-action](https://github.com/yusufkaraaslan/skill-seekers-action)** | GitHub Action for CI/CD | |
  314. | **[skill-seekers-plugin](https://github.com/yusufkaraaslan/skill-seekers-plugin)** | Claude Code plugin | |
  315. | **[homebrew-skill-seekers](https://github.com/yusufkaraaslan/homebrew-skill-seekers)** | Homebrew tap for macOS | |
  316. > **Want to contribute?** The website and configs repos are great starting points for new contributors!

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.