generate-image
Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.
Security Assessment
Detected risks:
About generate-image
The generate-image skill enables users to generate and edit high-quality images using advanced AI models such as FLUX and Gemini. This skill addresses the need for versatile image creation, allowing individuals to produce a wide range of visual content from photos and illustrations to concept art and visual assets. It simplifies the process of image generation and modification, making it accessible for users who may not have extensive design skills or resources.
FAQ
What types of images can I generate with this skill?
You can generate photos, artistic illustrations, visual assets for presentations, and concept art.
Do I need an API key to use the generate-image skill?
Yes, you must set up an OpenRouter API key to run the script successfully.
Can I edit existing images with this skill?
Yes, the skill supports editing existing images by specifying an input image and providing editing instructions.
What are the available models for image generation?
The default model is google/gemini-3-pro-image-preview, with additional options including black-forest-labs/flux.2-pro and flux.2-flex.
Are there any limitations to the types of diagrams I can create?
Yes, for technical diagrams such as flowcharts and circuit diagrams, you should use the scientific-schematics skill instead.
Install generate-image
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
davila7/claude-code-templates