Skill Seekers 🧩 Skill Open source
Turns docs sites, repos, PDFs and videos into Agent Skills and RAG-ready knowledge
- GitHub stars
- 15k
- Stars this week
- +64
- Forks
- 1.5k
- Licence
- MIT
- Last push
- 2026-09-30
- Maintainer
- yusufkaraaslan
pip install skill-seekersThird-party agent skills run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
Built on the open Agent Skills standard, so it works in every app that supports Agent Skills.
Aider
DSCODEAbout Skill Seekers
What it does
Skill Seekers is a Python command-line tool that turns documentation and code into Agent Skills and other AI-ready knowledge. You point it at a documentation site, a GitHub repository, a local codebase, a PDF or one of about fifteen other source types. It scrapes and organises the content, can use an LLM or your local coding agent to improve it, and packages the result as a SKILL.md skill with reference files. The same content can also be exported as chunks for retrieval pipelines and vector databases. When one skill combines several sources, it flags places where they conflict.
What is inside
- Sources: documentation sites (with
llms.txtand single-page-app handling), GitHub repositories, local code, PDF, Word, EPUB, Jupyter, OpenAPI, PowerPoint, AsciiDoc, HTML, RSS, man pages, YouTube or local video, Confluence, Notion and Slack or Discord exports - Code analysis: AST parsing, design-pattern detection and examples taken from tests
scan: detects the frameworks a project uses and creates a config for each- Export targets: Claude, Gemini, OpenAI, OpenCode and other LLM platforms, plus LangChain, LlamaIndex, Haystack, Chroma, FAISS, Weaviate, Qdrant and Pinecone
install-agent: copies a finished skill into the right folder for about twenty coding agents- MCP server with about forty tools for use from inside an agent
- A quality score with a pass threshold
Works with
The skills it produces use the standard format and install into Claude Code, Cursor, VS Code with Copilot, Amp, Goose, OpenCode, Windsurf, Cline, Roo Code, Aider, Kilo Code, Continue and more. The MCP server is documented for Claude Code, Cursor, Windsurf, Cline and IntelliJ.
How to install
It needs Python 3.10 or newer and Git:
pip install skill-seekersMaintenance and safety
The project is MIT licensed, actively developed and has a large test suite. It downloads whatever sources you point it at and, in API mode, sends content to the LLM provider you configure. Uploading to Claude needs your Anthropic API key. Generated skills are only as reliable as their sources, so read them before installing.
Who should use it
Developers who want an agent skill for a library, internal codebase or document set that has no official skill.
Pros
- About 18 source types and 22 export targets
- Installs generated skills into many agents
- MCP server and quality scoring included
Cons
- Output quality depends on sources and optional LLM enhancement
- Many optional extras make setup sprawling
Similar agent skills
All development workflow skills →
Superpowers 🧩 SkillFree
A skills library that makes coding agents plan, test-first and debug systematically
Matt Pocock's Skills 🧩 SkillOpen source
Small, composable engineering skills: grilling, TDD, specs, tickets and architecture review
Agent Skills (Addy Osmani) 🧩 SkillOpen source
25 lifecycle skills and commands that make agents spec, test, review and ship with discipline
Ponytail 🧩 SkillOpen source
Makes your coding agent write the minimum code a task needs, without cutting safety
Understand Anything 🧩 SkillOpen source
Turns a codebase into an interactive knowledge graph with tours, search and Q&A
Archify 🧩 SkillOpen source
Validated, interactive architecture, sequence and data-flow diagrams compiled from typed JSON