Which AI models are supported by this skill?

The skill supports Google Gemini 3 Pro (image preview) and Black Forest Labs FLUX.2 Pro and Dev versions via the OpenRouter API.

What credentials are required to use the image generator?

You need an OpenRouter API key configured in a .env file as OPENROUTER_API_KEY or set as an environment variable.

What file formats does the skill output?

The skill saves generated and edited images as high-quality PNG files by default, though you can specify custom output paths.

Is this skill suitable for technical and scientific diagrams?

Absolutely. It is specifically optimized for creating schematics, figures, and visual explanations required for technical and scientific documentation.

Can I edit an existing image instead of generating a new one?

Yes, you can use the --input flag to provide an existing image path and provide text instructions to modify colors, add elements, or change styles.

AI Image Generator & Editor

Name: AI Image Generator & Editor
Author: ricable

byricable

•

Design Tools

Generates and modifies high-quality scientific illustrations, diagrams, and concept visualizations using advanced AI models like FLUX and Gemini.

About

The Generate Image skill enables Claude to produce or transform visual assets directly within your development environment. By leveraging industry-leading models via OpenRouter—including FLUX.2 Pro and Gemini 3 Pro—it facilitates both text-to-image generation and sophisticated image-to-image editing. This tool is specifically designed for developers, researchers, and technical writers who need to create schematics, infographics, or visual explanations for documentation and scientific papers without breaking their terminal-based workflow.

Key Features

1 GitHub stars
Automatic .env configuration for secure API key management
Sophisticated image editing to modify, add, or remove elements
Multi-model support featuring FLUX.2 Pro and Gemini 3 Pro
Streamlined CLI integration for rapid asset generation
Support for multiple input formats including PNG, JPEG, and WebP

Use Cases

Creating high-resolution visual aids for presentations, posters, and infographics
Generating complex scientific diagrams and schematics for technical documentation
Editing existing UI mockups or concept art using natural language instructions

About

Key Features

1 GitHub stars
Automatic .env configuration for secure API key management
Sophisticated image editing to modify, add, or remove elements
Multi-model support featuring FLUX.2 Pro and Gemini 3 Pro
Streamlined CLI integration for rapid asset generation
Support for multiple input formats including PNG, JPEG, and WebP

Use Cases

Creating high-resolution visual aids for presentations, posters, and infographics
Generating complex scientific diagrams and schematics for technical documentation
Editing existing UI mockups or concept art using natural language instructions