imagen

This skill leverages Google Gemini's image generation model (`gemini-3-pro-image-preview`) to create images based on text prompts. It's designed for seamless integration into Claude Code sessions, enabling image creation for frontend UIs, documentation, visual representations of concepts, and more. It works across Windows, macOS, and Linux.

The skill takes a text prompt, calls the Google Gemini API, saves the generated image (PNG) to a specified location (defaults to the current directory), and returns the file path. It requires the `GEMINI_API_KEY` environment variable to be set and Python 3.6+ to run the provided script.

What It Does

Generates images from text prompts using the Google Gemini image generation model.

When To Use

When you need to generate images for frontend development, documentation, visualizing concepts, or creating UI assets directly within your coding environment.

Installation

Copy SKILL.md to your skills directory