skill-seekers

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills. Use when creating Claude skills from docs, scraping documentation, packaging websites into skills, or converting repos/PDFs to Claude knowledge.

jakerains/agentskills7 installsMITSynced Aug 26

Works with

Claude CodeCursorCodex CLIGitHub CopilotGemini CLI
---
name: skill-seekers
description: Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills. Use when creating Claude skills from docs, scraping documentation, packaging websites into skills, or converting repos/PDFs to Claude knowledge.
license: MIT
---

# Skill Seekers

**Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills automatically.**

## Quick Reference

### Installation
```bash
pip install skill-seekers
```

### Core Commands

```bash
# Scrape documentation website
skill-seekers scrape --config configs/react.json
skill-seekers scrape --url https://docs.example.com --name myskill

# Scrape GitHub repository
skill-seekers github --repo facebook/react

# Extract from PDF
skill-seekers pdf --pdf docs/manual.pdf --name myskill

# Combine multiple sources (docs + GitHub + PDF)
skill-seekers unified --config configs/react_unified.json

# Enhance the skill with AI
skill-seekers enhance output/myskill/

# Package into .zip for Claude
skill-seekers package output/myskill/
```

### Complete Workflow

```bash
# 1. Scrape documentation
skill-seekers scrape --url https://react.dev --name react

# 2. Enhance with AI (optional but recommended)
skill-seekers enhance output/react/

# 3. Package into zip
skill-seekers package output/react/

# 4. Upload output/react.zip to Claude at https://claude.ai/skills
```

## Key Features

| Feature | Description |
|---------|-------------|
| **Doc Scraping** | Scrape any documentation website |
| **GitHub Scraping** | Extract code, APIs, issues from repos |
| **PDF Extraction** | Extract text, tables, images from PDFs |
| **Unified Scraping** | Combine docs + code + PDF in one skill |
| **Conflict Detection** | Find discrepancies between docs and code |
| **AI Enhancement** | Improve SKILL.md quality automatically |
| **Async Mode** | 2-3x faster with `--async` flag |

## Output Structure

```
output/
├── myskill_data/     # Raw scraped data (cached)
└── myskill/          # Built skill directory
    ├── SKILL.md      # Main skill file (required)
    └── references/   # Categorized documentation
        ├── index.md
        ├── api.md
        └── ...
```

## Available Presets

```bash
skill-seekers scrape --config configs/godot.json     # Godot Engine
skill-seekers scrape --config configs/react.json     # React
skill-seekers scrape --config configs/vue.json       # Vue.js
skill-seekers scrape --config configs/django.json    # Django
skill-seekers scrape --config configs/fastapi.json   # FastAPI
```

## Config File Structure

```json
{
  "name": "myframework",
  "description": "When to use this skill",
  "base_url": "https://docs.myframework.com/",
  "selectors": {
    "main_content": "article",
    "title": "h1",
    "code_blocks": "pre code"
  },
  "url_patterns": {
    "include": ["/docs", "/guide"],
    "exclude": ["/blog", "/about"]
  },
  "rate_limit": 0.5,
  "max_pages": 500
}
```

## Navigation

For detailed information, see:
- `references/readme.md` - Full documentation and examples
- `references/quickstart.md` - Getting started guide
- `references/usage.md` - Complete command reference

More Writing & Documentation skills

paper-context-resolver

lllllllama/rigorpilot-skills

Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.

450.8k

repo-intake-and-plan

lllllllama/rigorpilot-skills

Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.

450.0k

minimal-run-and-audit

lllllllama/rigorpilot-skills

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

449.9k

← All Writing & Documentation skills

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY