Skill Seekers
@yusufkaraaslan
Transform 17 source types (docs, GitHub repos, PDFs, videos, Jupyter, Confluence, Notion, Slack/Discord) into AI-ready skills and RAG knowledge. 35 MCP tools for scraping, packaging, and exporting to vector databases. Supports 16+ LLM platforms.
概览
What is Skill Seekers?
A CLI tool that transforms 17 source types (documentation websites, GitHub repos, PDFs, videos, Jupyter Notebooks, Word documents, EPUBs, OpenAPI specs, PowerPoint presentations, RSS feeds, man pages, Confluence wikis, Notion pages, Slack/Discord exports, and more) into structured knowledge assets for AI systems. It serves as a universal preprocessing layer between raw documentation and AI targets including Claude, Gemini, OpenAI, RAG pipelines (LangChain, LlamaIndex, Haystack), vector databases (Pinecone, ChromaDB, FAISS, Qdrant), and AI coding assistants (Cursor, Windsurf, Cline, Continue.dev).
How to use Skill Seekers?
Install via pip install skill-seekers. Then run skill-seekers create <source> (e.g., a URL, GitHub repository, or local path) to ingest content. Finally, export the resulting asset to any target platform using skill-seekers package output/<name> --target <platform> (e.g., claude, langchain, cursor). Use skill-seekers video --url ... for video sources.
Key features of Skill Seekers
- Ingest from 17 source types: docs, GitHub, PDFs, videos, notebooks, wikis, and more
- Export to 16 AI platforms: Claude, Gemini, OpenAI, LangChain, LlamaIndex, Haystack, multiple vector DBs, and AI coding assistants
- AI-enhanced SKILL.md generation with 500+ line examples, patterns, and guides
- Smart chunking that preserves code blocks and maintains context for RAG pipelines
- Video extraction with transcripts, OCR, GPU auto-detection, and vision API fallback
- Battle-tested: 2,540+ tests, 24+ preset configs, production-ready
Use cases of Skill Seekers
- Build a production-grade AI Skill for Claude from a public API documentation site
- Preprocess a GitHub
