A collection of open-source skills for Claude Code.

1. Clone this repository or download the skill folder you want to use
2. Copy the skill folder to your Claude Code skills directory:
   • macOS/Linux: ~/.claude/skills/
   • Windows: %USERPROFILE%\.claude\skills\

For example, to install the gemini-image-generator skill:

# Clone the repository
git clone https://github.com/mkdev-me/claude-skills.git

# Copy the skill to your Claude Code skills directory
cp -r claude-skills/gemini-image-generator ~/.claude/skills/

3. Follow the skill-specific setup instructions in the skill's SKILL.md file

After installation, the skill should appear when you use Claude Code. You can verify by asking Claude Code to list available skills.

Generate images using Google Gemini's image generation capabilities.

• Python 3.8+
• A Google AI Studio API key

1. Copy the skill to your Claude Code skills directory (see above)

2. Navigate to the skill's scripts directory and set up the virtual environment:

   cd ~/.claude/skills/gemini-image-generator/scripts
   python3 -m venv venv
   ./venv/bin/pip install -r requirements.txt

3. Get your API key from Google AI Studio

4. Set the environment variable:

   export GEMINI_API_KEY="your-api-key-here"

   For persistent configuration, add this to your shell profile (~/.bashrc, ~/.zshrc, etc.):

   echo 'export GEMINI_API_KEY="your-api-key-here"' >> ~/.zshrc
   source ~/.zshrc

Once installed and configured, you can ask Claude Code to generate images:

• "Generate an image of a mountain sunset"
• "Create a logo for my app"
• "Make an image based on this reference photo"

• Text-to-image: Generate images from text descriptions
• Image-to-image: Use reference images for style guidance
• Multiple sizes: Support for 1K, 2K, and 4K output resolutions

Contributions are welcome! To add a new skill:

1. Create a new directory with your skill name
2. Include a SKILL.md file with the required frontmatter:

   ---
   name: your-skill-name
   description: Brief description of what your skill does
   ---

3. Add any necessary scripts in a scripts/ subdirectory
4. Update this README with your skill information
5. Submit a pull request

This project is licensed under the MIT License - see the LICENSE file for details.