Which AI models are supported by this skill?

The skill supports various models available via OpenRouter, primarily Google Gemini 3 Pro and Black Forest Labs FLUX.2 Pro for both generation and editing.

Is an API key required for this skill?

Yes, you must have an OpenRouter API key configured in a .env file or as an environment variable (OPENROUTER_API_KEY) to use the generation services.

What kind of scientific illustrations can I create?

The skill is optimized for scientific diagrams, schematics, infographics, and visual explanations, making it ideal for technical documentation.

Can I edit existing images instead of generating new ones?

Yes, by using the --input parameter, you can provide an existing image and use text prompts to modify colors, add or remove elements, or change styles.

Where are the generated images saved?

By default, images are saved as 'generated_image.png' in your current directory, though you can specify a custom name and path using the --output flag.

AI Image Generation & Editing

Name: AI Image Generation & Editing
Author: Microck

byMicrock

•

Herramientas de Diseño

Generates and modifies high-quality visual content, including scientific illustrations and diagrams, using advanced AI models like FLUX and Gemini.

Acerca de

This skill empowers Claude to create and refine visual assets directly within the development environment by leveraging OpenRouter's powerful image models. It provides a robust Python interface for generating new schematics, infographics, and artistic images from text prompts, while also supporting complex image editing tasks like color modification and element removal. Ideal for developers and researchers who need to produce high-quality figures, posters, or visual explanations without leaving their terminal workflow.

Características Principales

High-quality text-to-image generation using FLUX.2 Pro and Gemini 3 Pro
Advanced image-to-image editing to modify existing visual assets
Support for multiple output formats including PNG, JPEG, and WebP
81 GitHub stars
Seamless CLI integration for generating images within development environments
Automatic API key management via .env files or environment variables

Casos de Uso

Creating scientific diagrams and schematics for project documentation
Modifying existing UI mockups or branding assets via natural language commands
Generating conceptual visualizations and infographics for presentations

Acerca de

Características Principales

High-quality text-to-image generation using FLUX.2 Pro and Gemini 3 Pro
Advanced image-to-image editing to modify existing visual assets
Support for multiple output formats including PNG, JPEG, and WebP
81 GitHub stars
Seamless CLI integration for generating images within development environments
Automatic API key management via .env files or environment variables

Casos de Uso

Creating scientific diagrams and schematics for project documentation
Modifying existing UI mockups or branding assets via natural language commands
Generating conceptual visualizations and infographics for presentations