Overview
generate-image is an open-source data skill for Claude Code and compatible agents, published by K-Dense-AI. Its author describes it as: “Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos, illustrations, artwork, concept art, visual assets, logos, and image editing o…”. The project has 34k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/K-Dense-AI/scientific-agent-skills ~/.claude/skills/generate-image`.
What generate-image does
Generate and edit images through OpenRouter's Image API, which reaches Gemini, Seedream, Recraft, GPT-Image, Riverflow, and roughly thirty other models behind one request shape.
What’s inside
The SKILL.md for generate-image is organised into these sections:
- When to use
- API key
- Quick start
- Choosing a model
- Parameter support varies by model
- Writing the prompt
- Editing and reference images
- Worked examples
- Script parameters
- API shape
- Cost
- Notes and caveats
Installation
Add generate-image to your agent with:
git clone https://github.com/K-Dense-AI/scientific-agent-skills ~/.claude/skills/generate-imageReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
Neither the skill nor its repository names a specific agent. It uses the SKILL.md format, which several agents can load — check the repository for any agent-specific requirements.
License
generate-image is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in K-Dense-AI/scientific-agent-skills, an established project with 33,821 GitHub stars
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does generate-image do?
- Generate or edit images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos, illustrations, artwork, concept art, visual assets, logos, and image editing or compositing from reference images. For flowcharts, circuits, pathways, and other technical diagrams, use the scientific-schematics skill instead.
- How do I install generate-image?
- Run git clone https://github.com/K-Dense-AI/scientific-agent-skills ~/.claude/skills/generate-image in your agent, then reload your skills. Review the source at https://github.com/K-Dense-AI/scientific-agent-skills before installing.
- Is generate-image free to use?
- Yes. generate-image is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does generate-image come from?
- generate-image ships inside K-Dense-AI/scientific-agent-skills, a repository that contains 42 catalogued skills in total. The repository's 33,821 GitHub stars apply to that whole collection, not to this skill on its own.