h3-image-prompt-writing — Claude Code skill: features and install
The h3-image-prompt-writing Claude Code skill writes prompts for image generation and editing with MiniMax-H3-Image. It activates for requests to create an image or modify supplied references.
no license ★ 442 updated 2026-11-11
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a claude-codeWhat h3-image-prompt-writing does
The skill turns a brief request into a detailed prompt for image creation or reference editing. It lays out the image’s purpose, composition, subjects, visual style and wording; for edits, it assigns a role to each reference and specifies what changes or stays intact. It can also send the prompt to the MiniMax API when an image render is requested.
The finished prompt is written in English, while text shown inside the image stays in its intended language. Rendering through the API requires Python 3 and the MINIMAX_API_KEY environment variable; the script uses Python’s standard library. Without the key, the skill returns the prompt but cannot render the image.
What it helps with
- draft a prompt for a poster, infographic or UI screen
- specify image layout and exact wording for a generation request
- change an object while preserving other parts of a reference
- combine multiple references into one scene
Example prompts for the agent
- Write a prompt for a product launch poster with the headline “New Season”.
- Change the sofa in
sofa.pngto blue while keeping its shape and position. - Combine the room in
room.jpgwith the sofa insofa.pngin one image.
How to install h3-image-prompt-writing
1Skills CLI (Vercel)
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a claude-code2Manually: put the files in place
~/.claude/skills/h3-image-prompt-writing/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/h3-image-prompt-writing/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a codex2Manually: put the files in place
.agents/skills/h3-image-prompt-writing/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a cursor2Manually: put the files in place
.cursor/skills/h3-image-prompt-writing/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MiniMax-AI/MiniMax-H3-Image skills/h3-image-prompt-writing2Manually: put the files in place
.github/skills/h3-image-prompt-writing/SKILL.md1Skills CLI (Vercel)
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a gemini-cli2Platform CLI
gemini skills install https://github.com/MiniMax-AI/MiniMax-H3-Image --path skills/h3-image-prompt-writingManually: put the files in place
.devin/skills/h3-image-prompt-writing/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about h3-image-prompt-writing
How do I install h3-image-prompt-writing in Claude Code?
Run npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a claude-code. The skill file is at ~/.claude/skills/h3-image-prompt-writing/SKILL.md.
What does h3-image-prompt-writing do?
It drafts prompts for image generation and reference editing with MiniMax-H3-Image. On request, it can also send a prompt to the MiniMax API for rendering.
What does h3-image-prompt-writing need to render an image?
Rendering through the MiniMax API requires Python 3 and the MINIMAX_API_KEY environment variable. Prompt writing does not require the key.