imagen – Design & UI skill for AI agents

Imagen - AI Image Generation Skill

Overview

This skill bundles a reviewed standard-library helper for an explicitly selected supported Gemini image model; model availability and pricing must be checked before an authorized call. 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

Use within the actual host's image-tool workflow and authorized provider scope 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

1. Takes a text prompt describing the desired image

2. Calls Google Gemini API with image generation configuration

3. Saves the generated image to a specified location (defaults to current directory)

4. Returns the file path for use in your project

Usage

Python (Cross-Platform - Recommended)

# Basic usage
python scripts/generate_image.py --model "$GEMINI_MODEL" "A futuristic city skyline at sunset" "./generated-image.png"

# With custom output path
python scripts/generate_image.py "A minimalist app icon for a music player" "./assets/icons/music-icon.png"

# With custom size
python scripts/generate_image.py --size 2K "High resolution landscape" "./wallpaper.png"

Requirements

• GEMINI_API_KEY environment variable must be set
• Python 3.10+ (standard library helper, no pip install needed)
• Explicit reviewed GEMINI_MODEL or --model; verify supported size/API schema
• Existing authorized private output directory and a new .png filename

Data, cost and output checks

Prompts are transmitted to Google and may incur provider charges; approve the service/data and cost scope first. Do not auto-install credentials, retry an uncertain billable call or overwrite files. The bundled helper refuses redirects, bounds response bytes and validates PNG MIME/signature; it is not a full image decoder or proof of visual correctness. The socket timeout is not a guaranteed total wall-clock budget. Review dimensions, content and rights after delivery, and publish only when authorized. Use the host's purpose-built image tool where its contract requires it.

[Current Gemini image API](https://ai.google.dev/gemini-api/docs/image-generation); [upstream provenance](UPSTREAM-NOTICE.md).

Output

Generated images are saved as PNG files. The script returns:

• Success: Path to the generated image
• Failure: Error message with details

Examples

Frontend Development

User: "I need a hero image for my landing page - something abstract and tech-focused"
-> Generates and saves image, provides path for use in HTML/CSS

Documentation

User: "Create a diagram showing microservices architecture"
-> Generates visual representation, ready for README or docs

UI Assets

User: "Generate a placeholder avatar image for the user profile component"
-> Creates image in appropriate size for component use

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

API compatibility caveat

This helper implements the generateContent envelope; the current linked image guide demonstrates the Interactions API, whose endpoint, request fields and response shape differ. Do not pass a model advertised only for Interactions to this helper or assume its imageSize options are supported. Verify the selected model explicitly supports the helper's generateContent schema before any billable request; otherwise use a reviewed provider adapter or the host image tool. No API call or platform compatibility test was performed here. Prompt command-line arguments can appear in process listings/history, so use only non-sensitive prompts with this interface. Partial output may remain after a disk-write error; inspect it privately and choose a new path rather than automatically retrying the provider.