#2121st of 50 in Data and scraping for AI
skill_seekers
CLI that turns docs, repos, PDFs and videos into AI skills and RAG data
- Stars
- 15.3k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Sep 2026
- Language
- Python
12,785 on 21 Apr 202615,299 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Skill Seekers is a Python CLI that scrapes 18 source types (doc sites, GitHub repos, PDFs, Word, Jupyter, OpenAPI, YouTube, Confluence, Notion and others) and packages the result for 22 targets. Targets include Claude/Gemini/OpenAI skills, LangChain and LlamaIndex documents, and vector stores such as Chroma, Qdrant and Pinecone. It also ships an MCP server with 40 tools and can install skills into 19 coding agents.
Who it is for: Developers preparing docs and codebases as context for AI agents or RAG
Strengths
- Handles 18 source types and exports to 22 targets from one scrape
- AI enhancement runs via API providers or local agents such as Claude Code, no API cost
- Ships an MCP server (40 tools) with stdio and HTTP transports
- Doc scraper checks sitemap.xml and llms.txt, and falls back to headless browser rendering
Weaknesses
- Quality of SKILL.md depends on an external LLM agent or API for enhancement
- Video visual extraction needs extra installs, including GPU-specific PyTorch and easyocr
- Large doc sets (10K+ pages) need a separate streaming mode and take long
- Speed and quality claims like '99% faster' are not backed by published benchmarks
What it needs
- GPU optional
- Docker + Compose
- Needs Python 3.10+, Git, Anthropic/Gemini/OpenAI API or local agent (optional), Whisper, PyTorch, easyocr (video extras)
- Models: Claude, Gemini, OpenAI, Kimi, MiniMax
- port 8765
Quick answers
Is skill_seekers open source?
Yes. Its code is on GitHub under the MIT license.
Can you run skill_seekers with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does skill_seekers need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Data and scraping for AI
See all 50| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 90 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 88 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |