# Pack to Claude Skill Pipeline
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](https://github.com/jmanhype/pack2skill/releases)
[](https://github.com/jmanhype/pack2skill/issues)
[](https://github.com/jmanhype/pack2skill/stargazers)
A comprehensive system for capturing workflows and automatically generating Claude Skills from recorded user interactions.
## Overview
This pipeline transforms real-world workflows into Claude Skills through four progressive phases:
1. **Phase 1 (MVP)**: Recording & Basic Skill Generation
2. **Phase 2**: Improving Skill Quality (confidence, descriptions, robustness)
3. **Phase 3**: Collaboration & Deployment (team features)
4. **Phase 4**: Ecosystem Integration and Marketplace
## Features
- **Workflow Recording**: Capture screen video and user interaction events
- **Vision-Language Analysis**: Extract meaningful steps from video frames
- **Automated Skill Generation**: Create Claude Skills with proper structure and metadata
- **Confidence Scoring**: Rate the reliability of each generated step
- **Team Collaboration**: Version control, sharing, and deployment features
- **Ecosystem Integration**: Connect with Claude's skill marketplace and MCP plugins
## Quick Start
```bash
# Install dependencies
pip install -r requirements.txt
# Record a workflow
python -m pack2skill record --output my_workflow.json
# Generate a skill
python -m pack2skill generate my_workflow.json --output ./skills/
# Install the skill
python -m pack2skill install ./skills/my-skill/
```
## Project Structure
```
pack2skill/
├── core/ # Core functionality
│ ├── recorder/ # Workflow recording (screen + events)
│ ├── analyzer/ # Video frame analysis and captioning
│ ├── generator/ # Skill generation logic
│ └── utils/ # Shared utilities
├── quality/ # Phase 2: Quality improvements
│ ├── confidence.py # Confidence scoring
│ ├── description.py # Description optimization
│ └── robustness.py # Edge case handling
├── team/ # Phase 3: Team features
│ ├── versioning.py # Version control integration
│ ├── deployment.py # Skill deployment
│ └── testing.py # Testing framework
├── ecosystem/ # Phase 4: Ecosystem integration
│ ├── marketplace.py # Marketplace features
│ └── integrations.py # MCP and plugin support
├── cli/ # Command-line interface
└── tests/ # Test suite
```
## Requirements
- Python 3.9+
- FFmpeg (for screen recording)
- CUDA-capable GPU (recommended for vision models)
## Documentation
See the [docs/](docs/) directory for detailed documentation:
- [Installation Guide](docs/installation.md)
- [Recording Guide](docs/recording.md)
- [Skill Generation](docs/generation.md)
- [Team Setup](docs/team-setup.md)
- [API Reference](docs/api-reference.md)
## Contributing
We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
## License
MIT License - see [LICENSE](LICENSE) for details.
## Acknowledgments
Built for the Claude Skills ecosystem by Anthropic.
Raw data
{
"_id": null,
"home_page": "https://github.com/jmanhype/pack2skill",
"name": "pack2skill",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "claude, claude-skills, workflow-automation, skill-generation, ai",
"author": "Pack2Skill Team",
"author_email": "Pack2Skill Team <contact@pack2skill.dev>",
"download_url": "https://files.pythonhosted.org/packages/01/07/24a26eee52670f8aa151f7bc1dbf3cbda8d33aef35025a4c95ae2d23b3b1/pack2skill-0.1.0.tar.gz",
"platform": null,
"description": "# Pack to Claude Skill Pipeline\n\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n[](https://github.com/jmanhype/pack2skill/releases)\n[](https://github.com/jmanhype/pack2skill/issues)\n[](https://github.com/jmanhype/pack2skill/stargazers)\n\nA comprehensive system for capturing workflows and automatically generating Claude Skills from recorded user interactions.\n\n## Overview\n\nThis pipeline transforms real-world workflows into Claude Skills through four progressive phases:\n\n1. **Phase 1 (MVP)**: Recording & Basic Skill Generation\n2. **Phase 2**: Improving Skill Quality (confidence, descriptions, robustness)\n3. **Phase 3**: Collaboration & Deployment (team features)\n4. **Phase 4**: Ecosystem Integration and Marketplace\n\n## Features\n\n- **Workflow Recording**: Capture screen video and user interaction events\n- **Vision-Language Analysis**: Extract meaningful steps from video frames\n- **Automated Skill Generation**: Create Claude Skills with proper structure and metadata\n- **Confidence Scoring**: Rate the reliability of each generated step\n- **Team Collaboration**: Version control, sharing, and deployment features\n- **Ecosystem Integration**: Connect with Claude's skill marketplace and MCP plugins\n\n## Quick Start\n\n```bash\n# Install dependencies\npip install -r requirements.txt\n\n# Record a workflow\npython -m pack2skill record --output my_workflow.json\n\n# Generate a skill\npython -m pack2skill generate my_workflow.json --output ./skills/\n\n# Install the skill\npython -m pack2skill install ./skills/my-skill/\n```\n\n## Project Structure\n\n```\npack2skill/\n\u251c\u2500\u2500 core/ # Core functionality\n\u2502 \u251c\u2500\u2500 recorder/ # Workflow recording (screen + events)\n\u2502 \u251c\u2500\u2500 analyzer/ # Video frame analysis and captioning\n\u2502 \u251c\u2500\u2500 generator/ # Skill generation logic\n\u2502 \u2514\u2500\u2500 utils/ # Shared utilities\n\u251c\u2500\u2500 quality/ # Phase 2: Quality improvements\n\u2502 \u251c\u2500\u2500 confidence.py # Confidence scoring\n\u2502 \u251c\u2500\u2500 description.py # Description optimization\n\u2502 \u2514\u2500\u2500 robustness.py # Edge case handling\n\u251c\u2500\u2500 team/ # Phase 3: Team features\n\u2502 \u251c\u2500\u2500 versioning.py # Version control integration\n\u2502 \u251c\u2500\u2500 deployment.py # Skill deployment\n\u2502 \u2514\u2500\u2500 testing.py # Testing framework\n\u251c\u2500\u2500 ecosystem/ # Phase 4: Ecosystem integration\n\u2502 \u251c\u2500\u2500 marketplace.py # Marketplace features\n\u2502 \u2514\u2500\u2500 integrations.py # MCP and plugin support\n\u251c\u2500\u2500 cli/ # Command-line interface\n\u2514\u2500\u2500 tests/ # Test suite\n```\n\n## Requirements\n\n- Python 3.9+\n- FFmpeg (for screen recording)\n- CUDA-capable GPU (recommended for vision models)\n\n## Documentation\n\nSee the [docs/](docs/) directory for detailed documentation:\n\n- [Installation Guide](docs/installation.md)\n- [Recording Guide](docs/recording.md)\n- [Skill Generation](docs/generation.md)\n- [Team Setup](docs/team-setup.md)\n- [API Reference](docs/api-reference.md)\n\n## Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n## Acknowledgments\n\nBuilt for the Claude Skills ecosystem by Anthropic.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Transform workflows into Claude Skills automatically",
"version": "0.1.0",
"project_urls": {
"Changelog": "https://github.com/jmanhype/pack2skill/releases",
"Documentation": "https://github.com/jmanhype/pack2skill#readme",
"Homepage": "https://github.com/jmanhype/pack2skill",
"Issues": "https://github.com/jmanhype/pack2skill/issues",
"Repository": "https://github.com/jmanhype/pack2skill"
},
"split_keywords": [
"claude",
" claude-skills",
" workflow-automation",
" skill-generation",
" ai"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "bab8a6f684c7a006c6dde43ce388ded38e606afb611f52a18829c707fd768e04",
"md5": "b504a95dfdc6cc0d618997aa89a54c94",
"sha256": "43113cf23b74711be87ab74c3a9da5cbeb3b24d100ddee3db055ab080e7879dc"
},
"downloads": -1,
"filename": "pack2skill-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b504a95dfdc6cc0d618997aa89a54c94",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 40067,
"upload_time": "2025-11-06T22:29:15",
"upload_time_iso_8601": "2025-11-06T22:29:15.859157Z",
"url": "https://files.pythonhosted.org/packages/ba/b8/a6f684c7a006c6dde43ce388ded38e606afb611f52a18829c707fd768e04/pack2skill-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "010724a26eee52670f8aa151f7bc1dbf3cbda8d33aef35025a4c95ae2d23b3b1",
"md5": "662cfdbde3d204c90a5e38df9c8d223d",
"sha256": "a0800543588828a10abd248f2ab955e05a9e94a30eabe02d0a3d7b84de3bdd75"
},
"downloads": -1,
"filename": "pack2skill-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "662cfdbde3d204c90a5e38df9c8d223d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 57658,
"upload_time": "2025-11-06T22:29:16",
"upload_time_iso_8601": "2025-11-06T22:29:16.991044Z",
"url": "https://files.pythonhosted.org/packages/01/07/24a26eee52670f8aa151f7bc1dbf3cbda8d33aef35025a4c95ae2d23b3b1/pack2skill-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-11-06 22:29:16",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "jmanhype",
"github_project": "pack2skill",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "transformers",
"specs": [
[
">=",
"4.35.0"
]
]
},
{
"name": "torch",
"specs": [
[
">=",
"2.0.0"
]
]
},
{
"name": "pillow",
"specs": [
[
">=",
"10.0.0"
]
]
},
{
"name": "opencv-python",
"specs": [
[
">=",
"4.8.0"
]
]
},
{
"name": "pytesseract",
"specs": [
[
">=",
"0.3.10"
]
]
},
{
"name": "pynput",
"specs": [
[
">=",
"1.7.6"
]
]
},
{
"name": "pyyaml",
"specs": [
[
">=",
"6.0"
]
]
},
{
"name": "openai",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "anthropic",
"specs": [
[
">=",
"0.7.0"
]
]
},
{
"name": "ffmpeg-python",
"specs": [
[
">=",
"0.2.0"
]
]
},
{
"name": "click",
"specs": [
[
">=",
"8.1.0"
]
]
},
{
"name": "tqdm",
"specs": [
[
">=",
"4.65.0"
]
]
},
{
"name": "python-dateutil",
"specs": [
[
">=",
"2.8.2"
]
]
},
{
"name": "requests",
"specs": [
[
">=",
"2.31.0"
]
]
},
{
"name": "pytest",
"specs": [
[
">=",
"7.4.0"
]
]
},
{
"name": "pytest-cov",
"specs": [
[
">=",
"4.1.0"
]
]
},
{
"name": "pytest-asyncio",
"specs": [
[
">=",
"0.21.0"
]
]
},
{
"name": "black",
"specs": [
[
">=",
"23.0.0"
]
]
},
{
"name": "flake8",
"specs": [
[
">=",
"6.0.0"
]
]
},
{
"name": "mypy",
"specs": [
[
">=",
"1.5.0"
]
]
},
{
"name": "pre-commit",
"specs": [
[
">=",
"3.3.0"
]
]
}
],
"lcname": "pack2skill"
}
JSON
