Auto-detects NVIDIA (CUDA), AMD (ROCm), or CPU-only GPU and installs the correct PyTorch variant + easyocr + all visual extraction dependencies. Removes easyocr from video-full pip extras to avoid pulling ~2GB of wrong CUDA packages on non-NVIDIA systems. New files: - video_setup.py (835 lines): GPU detection, PyTorch install, ROCm config, venv checks, system dep validation, module selection, verification - test_video_setup.py (60 tests): Full coverage of detection, install, verify Updated docs: CHANGELOG, AGENTS.md, CLAUDE.md, README.md, CLI_REFERENCE, FAQ, TROUBLESHOOTING, installation guide, video dependency plan All 2523 tests passing (15 skipped). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Skill Seekers Documentation
Complete documentation for Skill Seekers v3.1.0
Welcome!
This is the official documentation for Skill Seekers - the universal tool for converting documentation, code, and PDFs into AI-ready skills.
Where Should I Start?
🚀 I'm New Here
Start with our Getting Started guides:
- Installation - Install Skill Seekers
- Quick Start - Create your first skill in 3 commands
- Your First Skill - Complete walkthrough
- Next Steps - Where to go from here
📖 I Want to Learn
Explore our User Guides:
- Core Concepts - How Skill Seekers works
- Scraping Guide - All scraping options
- Enhancement Guide - AI enhancement explained
- Packaging Guide - Export to platforms
- Workflows Guide - Enhancement workflows
- Troubleshooting - Common issues
📚 I Need Reference
Look up specific information:
- CLI Reference - All 20 commands
- MCP Reference - 26 MCP tools
- Config Format - JSON specification
- Environment Variables - All env vars
🚀 I'm Ready for Advanced Topics
Power user features:
- MCP Server Setup - MCP integration
- MCP Tools Deep Dive - Advanced MCP usage
- Custom Workflows - Create workflows
- Multi-Source Scraping - Combine sources
Quick Reference
The 3 Commands
# 1. Install
pip install skill-seekers
# 2. Create skill
skill-seekers create https://docs.django.com/
# 3. Package for Claude
skill-seekers package output/django --target claude
Common Commands
# Scrape documentation
skill-seekers scrape --config react
# Analyze GitHub repo
skill-seekers github --repo facebook/react
# Extract PDF
skill-seekers pdf manual.pdf --name docs
# Analyze local code
skill-seekers analyze --directory ./my-project
# Enhance skill
skill-seekers enhance output/my-skill/
# Package for platform
skill-seekers package output/my-skill/ --target claude
# Upload
skill-seekers upload output/my-skill-claude.zip
# List workflows
skill-seekers workflows list
Documentation Structure
docs/
├── README.md # This file - start here
├── ARCHITECTURE.md # How docs are organized
│
├── getting-started/ # For new users
│ ├── 01-installation.md
│ ├── 02-quick-start.md
│ ├── 03-your-first-skill.md
│ └── 04-next-steps.md
│
├── user-guide/ # Common tasks
│ ├── 01-core-concepts.md
│ ├── 02-scraping.md
│ ├── 03-enhancement.md
│ ├── 04-packaging.md
│ ├── 05-workflows.md
│ └── 06-troubleshooting.md
│
├── reference/ # Technical reference
│ ├── CLI_REFERENCE.md # 20 commands
│ ├── MCP_REFERENCE.md # 26 MCP tools
│ ├── CONFIG_FORMAT.md # JSON spec
│ └── ENVIRONMENT_VARIABLES.md
│
└── advanced/ # Power user topics
├── mcp-server.md
├── mcp-tools.md
├── custom-workflows.md
└── multi-source.md
By Use Case
I Want to Build AI Skills
For Claude, Gemini, ChatGPT:
I Want to Build RAG Pipelines
For LangChain, LlamaIndex, vector DBs:
I Want AI Coding Assistance
For Cursor, Windsurf, Cline:
- Your First Skill
- Local Codebase Analysis
skill-seekers install-agent --agent cursor
Version Information
- Current Version: 3.1.0
- Last Updated: 2026-02-16
- Python Required: 3.10+
Contributing to Documentation
Found an issue? Want to improve docs?
- Edit files in the
docs/directory - Follow the existing structure
- Submit a PR
See Contributing Guide for details.
External Links
- Main Repository: https://github.com/yusufkaraaslan/Skill_Seekers
- Website: https://skillseekersweb.com/
- PyPI: https://pypi.org/project/skill-seekers/
- Issues: https://github.com/yusufkaraaslan/Skill_Seekers/issues
License
MIT License - see LICENSE file.
Happy skill building! 🚀