Files
wehub-resource-sync 2cab53bc94
Test Vector Database Adaptors / Test MCP Vector DB Tools (push) Has been cancelled
Tests / Code Quality (Ruff & Mypy) (push) Has been cancelled
Tests / Fast Unit Tests (parallel) (macos-latest, 3.11) (push) Has been cancelled
Tests / Fast Unit Tests (parallel) (macos-latest, 3.12) (push) Has been cancelled
Tests / Tests (push) Has been cancelled
Docker Publish / Build and Push Docker Images (map[description:Skill Seekers CLI - Convert documentation to AI skills dockerfile:Dockerfile name:skill-seekers]) (push) Has been cancelled
Docker Publish / Build and Push Docker Images (map[description:Skill Seekers MCP Server - 25 tools for AI assistants dockerfile:Dockerfile.mcp name:skill-seekers-mcp]) (push) Has been cancelled
Docker Publish / Test Docker Images (push) Has been cancelled
Tests / Fast Unit Tests (parallel) (ubuntu-latest, 3.10) (push) Has been cancelled
Tests / Fast Unit Tests (parallel) (ubuntu-latest, 3.11) (push) Has been cancelled
Tests / Fast Unit Tests (parallel) (ubuntu-latest, 3.12) (push) Has been cancelled
Tests / Serial / Integration / E2E Tests (push) Has been cancelled
Tests / MCP Server Tests (push) Has been cancelled
Test Vector Database Adaptors / Test chroma Adaptor (push) Has been cancelled
Test Vector Database Adaptors / Test faiss Adaptor (push) Has been cancelled
Test Vector Database Adaptors / Test qdrant Adaptor (push) Has been cancelled
Test Vector Database Adaptors / Test weaviate Adaptor (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:46:28 +08:00

4.1 KiB

⚠️ DEPRECATED: This document is outdated and uses old CLI patterns.

For up-to-date documentation, please see:

This file is kept for historical reference only.


Quick Start Guide

🚀 3 Steps to Create a Skill

Step 1: Install Dependencies

pip3 install requests beautifulsoup4

Note: Skill_Seekers automatically checks for llms.txt files first, which is 10x faster when available.

Step 2: Run the Tool

Option A: Use a Preset (Easiest)

skill-seekers create --config configs/godot.json

Option B: Interactive Mode

skill-seekers create --interactive

Option C: Quick Command

skill-seekers create --name react --url https://react.dev/

Option D: Unified Multi-Source (NEW - v2.0.0)

# Combine documentation + GitHub code in one skill
skill-seekers create --config configs/react_unified.json

Detects conflicts between docs and code automatically!

# LOCAL enhancement (no API key, uses Claude Code Max)
skill-seekers enhance output/godot/

This takes 60 seconds and dramatically improves the SKILL.md quality!

Step 4: Package the Skill

skill-seekers package output/godot/

Done! You now have godot.zip ready to use.


📋 Available Presets

# Godot Engine
skill-seekers create --config configs/godot.json

# React
skill-seekers create --config configs/react.json

# Vue.js
skill-seekers create --config configs/vue.json

# Django
skill-seekers create --config configs/django.json

# FastAPI
skill-seekers create --config configs/fastapi.json

# Unified Multi-Source (NEW!)
skill-seekers create --config configs/react_unified.json
skill-seekers create --config configs/django_unified.json
skill-seekers create --config configs/fastapi_unified.json
skill-seekers create --config configs/godot_unified.json

Using Existing Data (Fast!)

If you already scraped once:

skill-seekers create --config configs/godot.json

# When prompted:
✓ Found existing data: 245 pages
Use existing data? (y/n): y

# Builds in seconds!

Or use --skip-scrape:

skill-seekers create --config configs/godot.json --skip-scrape

# 1. Install (once)
pip3 install requests beautifulsoup4

# 2. Scrape React docs with LOCAL enhancement
skill-seekers create --config configs/react.json --enhance-local
# Wait 15-30 minutes (scraping) + 60 seconds (enhancement)

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

# 4. Use react.zip in Claude!

Alternative: Enhancement after scraping

# 2a. Scrape only (no enhancement)
skill-seekers create --config configs/react.json

# 2b. Enhance later
skill-seekers enhance output/react/

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

💡 Pro Tips

Test with Small Pages First

Edit config file:

{
  "max_pages": 20  // Test with just 20 pages
}

Rebuild Instantly

# After first scrape, you can rebuild instantly:
skill-seekers create --config configs/react.json --skip-scrape

Create Custom Config

# Copy a preset
cp configs/react.json configs/myframework.json

# Edit it
nano configs/myframework.json

# Use it
skill-seekers create --config configs/myframework.json

📁 What You Get

output/
├── godot_data/          # Raw scraped data (reusable!)
└── godot/               # The skill
    ├── SKILL.md        # With real code examples!
    └── references/     # Organized docs

Need Help?

See README.md for:

  • Complete documentation
  • Config file structure
  • Troubleshooting
  • Advanced usage

🎮 Let's Go!

# Godot
skill-seekers create --config configs/godot.json

# Or interactive
skill-seekers create --interactive

That's it! 🚀