
Imagen
This wraps Google Gemini's image generation API so you can create images directly from Claude Code without leaving your workflow. You get a simple Python script that takes a text prompt and spits out a PNG file, no dependencies beyond the standard library. Handy when you're building a frontend and need placeholder images, mock assets, or quick visual concepts without context switching to a separate image tool. Just set your GEMINI_API_KEY and run the script with your prompt. The quality depends entirely on Gemini's model, but the convenience of generating images inline while coding is the real win here.
- skills.sh installs
- 639
- GitHub stars
- 454
- last updated
- Aug 21, 2026
Install
$ npx -y skills add sanjay3290/ai-skills --skill imagen --agent claude-codeInstalls into .claude/skills of the current project.
Files
Imagen - AI Image Generation Skill
Overview
This skill generates images using Google Gemini's image generation model (gemini-3-pro-image-preview). It enables seamless image creation during any Claude Code session - whether you're building frontend UIs, creating documentation, or need visual representations of concepts.
Cross-Platform: Works on Windows, macOS, and Linux.
When to Use This Skill
Automatically activate this skill when:
- User requests image generation (e.g., "generate an image of...", "create a picture...")
- Frontend development requires placeholder or actual images
- Documentation needs illustrations or diagrams
- Visualizing concepts, architectures, or ideas
- Creating icons, logos, or UI assets
- Any task where an AI-generated image would be helpful
How It Works
- Takes a text prompt describing the desired image
- Calls Google Gemini API with image generation configuration
- Saves the generated image to a specified location (defaults to current directory)
- Returns the file path for use in your project
Usage
Python (Cross-Platform - Recommended)
Sponsors
Details
- Repository
- github.com/sanjay3290/ai-skills
- Categories
- AI & Agent Building, Design & UI/UX
- License
- Apache-2.0
- First seen
- Jun 3, 2026