AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
Skill_Seekers
Skill_Seekers logo

Skill_Seekers

Active·★ 15.2k·MIT·Updated 2026-09-30
★ Most Popular★ Trending

Skill Seeker is an automated tool that converts documentation websites, GitHub repositories and PDF files into production-ready Claude AI skills. The README describes a pipeline: it scrapes multiple sources, analyses code repositories with deep AST parsing, detects conflicts between documentation and the code, organises content into categorised reference files, enhances it with AI to pull out the best examples and concepts, and packages everything into an uploadable ZIP. The claimed result is a skill for any framework or API in 20 to 40 minutes instead of hours of manual work.

Documentation scraping detects llms.txt files, PDF support was added in v1.2.0, GitHub scraping in v2.0.0, and a unified multi-source mode combines them. Since v2.5.0 it also targets four platforms: Claude (ZIP with YAML, needs ANTHROPIC_API_KEY), Google Gemini (tar.gz, GOOGLE_API_KEY), OpenAI ChatGPT (ZIP plus vector store, OPENAI_API_KEY) and a generic Markdown export that needs no key, selected with a --target flag and optional dependencies such as pip install skill-seekers[gemini]. A companion site offers 24+ preset configs. The licence is MIT.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-24.

License
MIT
Latest release
v3.10.0 · 2026-09-30
Last commit
2026-09-30
Contributors
50
Forks
1,542
Open issues and PRs
51
First published
2025-10-17
PyPI package
skill-seekers 3.10.0 · 651 downloads last week

Source: GitHub, npm and PyPI public APIs.

#Claude AI#Documentation Automation#GitHub Analysis#PDF Processing#Python#Web Browsing#Coding#Data Analysis
$ Install
$ pip install skill-seekers
↗ Visit site★ GitHub
01

Features

01Documentation Scraping
02PDF Support
03GitHub Repository Scraping
04Unified Multi-Source Scraping
05Multi-LLM Platform Support
02

Why choose it

+Combines docs sites, GitHub repositories and PDFs into one skill, with conflict detection between docs and code.
+Uses AST parsing of code and detects llms.txt files, rather than only scraping page text.
+Exports for Claude, Gemini, OpenAI and generic Markdown through one --target flag.
+MIT licensed, with 24+ preset configs and a public development roadmap.
03

Trade-offs

!The AI enhancement and auto-upload steps need an API key for the chosen platform (Anthropic, Google or OpenAI), which adds cost.
!The 20 to 40 minute time and quality of the generated skills are the project's claims and depend on the size and quality of the source docs.
!Scraping documentation sites and repositories should respect each site's terms, and generated skills still need reviewing before use.
05

Maintenance check

ActiveChecked: 2026-10-25
Last commit
2026-09-30
Commits, last 90 days
94
Releases, last 90 days
3
Latest release
v3.10.0 (2026-09-30)
Open issues
51
Recent issues with at least one comment
2/8
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 0, 18, 1, 1, 33, 10, 3, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #172 [FEATURE] How about one online market?2 comments · 2025-10-30
  • #260 🌏 帮助改进中文 README 翻译 / Help Improve Chinese README Translation1 comments · 2026-01-21
  • #241 [C4.3] Add code complexity metrics to ARCHITECTURE.md1 comments · 2026-01-04
  • #205 [A1.8] Add smart skill detection and auto-install1 comments · 2025-11-30
  • #167 feat: Version tracking for official vendor tutorials - Auto-detect API changes1 comments · 2025-10-29

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You want to turn a framework's docs site, GitHub repo and PDFs into one Claude skill instead of writing it by hand.
  • You want code analysed with AST parsing and conflicts between docs and code flagged.
  • You need output for Claude, Gemini, OpenAI or generic Markdown through one `--target` flag.
Look elsewhere if
  • You want an agent to read documents live: it builds skill packages ahead of time.
  • You cannot pay for the AI enhancement and upload steps: they need an Anthropic, Google or OpenAI key.
  • You would ship generated skills without review: the README's time and quality claims depend on the sources.
06

How it differs

kreuzberg logovs kreuzberg★ 9.5k

Kreuzberg extracts text from files for any pipeline. Skill Seekers scrapes docs and repos and packages the result as a skill.

Full comparison →
07

Compatibility

Claude AI
Native
Verified via docs
Google Gemini
Supported
Verified via docs
OpenAI ChatGPT
Supported
Verified via docs
Generic Markdown
Partial
Verified via docs
Model Context Protocol
Integrated
Verified via docs
08

Quick start

1
$ pip install skill-seekers
09

Use cases

↳Create skills from documentation and GitHub repos with conflict detection (for developers)
↳Generate skills for game engines like Godot and Unity (for game devs)
↳Combine internal documentation and code repositories into a single source of truth (for teams)
10

Alternatives

⚡Top VS:
VSkreuzberg★9.5k→VS1Panel★37.3k→VSAgently★1.7k→VSindex★2.4k→
kreuzberg logo
kreuzberg★ 9.5k
A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 50+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.
VSCompare→
1Panel logo
1Panel★ 37.3k
🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.
VSCompare→
Agently logo
Agently★ 1.7k
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code
VSCompare→
index logo
index★ 2.4k
The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web
VSCompare→
fastapi_mcp logo
fastapi_mcp★ 12.0k
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
VSCompare→
inspector logo
inspector★ 11.2k
Visual testing tool for MCP servers
VSCompare→
mcp-use logo
mcp-use★ 10.8k
mcp-use is the easiest way to interact with mcp servers with custom agents
VSCompare→
lowdefy logo
lowdefy★ 3.0k
The config web stack for business apps - build internal tools, client portals, web apps, admin panels, dashboards, web sites, and CRUD apps with YAML or JSON.
VSCompare→
See all alternatives →

Featured in these lists

  • Best Tools to Turn PDFs and Office Files into Markdown for AI Agents

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
yusufkaraaslan /
Skill_Seekers
↗

Turn documentation sites, GitHub repos and PDFs into AI skills

15.2k1.5kMIT
Last commit4w ago
StatusActive
CategoryDev Tooling
Contributors50
Latest releasev3.10.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.