# h3-image-prompt-writing

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.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 442 repo stars
- Author: MiniMax-AI
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/MiniMax-AI/MiniMax-H3-Image/tree/HEAD/skills/h3-image-prompt-writing/SKILL.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/h3-image-prompt-writing

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/h3-image-prompt-writing/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/h3-image-prompt-writing/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/h3-image-prompt-writing/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/h3-image-prompt-writing/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install MiniMax-AI/MiniMax-H3-Image skills/h3-image-prompt-writing
```

2. **Manually: put the files in place**
- File: `.github/skills/h3-image-prompt-writing/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/MiniMax-AI/MiniMax-H3-Image --path skills/h3-image-prompt-writing
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/h3-image-prompt-writing/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/MiniMax-AI/MiniMax-H3-Image/tree/HEAD/skills/h3-image-prompt-writing/SKILL.md

## When to use it
- 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
- Write a prompt for a product launch poster with the headline “New Season”.
- Change the sofa in `sofa.png` to blue while keeping its shape and position.
- Combine the room in `room.jpg` with the sofa in `sofa.png` in one image.

## Similar
- [ai-image-generation](https://affpapa.org/en/nevibecode/skills/prime-skills-ai-image-generation.md) — skill · 393900 installs
- [scenario-image](https://affpapa.org/en/nevibecode/skills/scenario-image.md) — skill · 1100 installs
- [scenario-mai-image](https://affpapa.org/en/nevibecode/skills/scenario-mai-image.md) — skill · 837 installs
- [linkfox-multimodal-generate-image](https://affpapa.org/en/nevibecode/skills/linkfox-multimodal-generate-image.md) — skill · 405 installs
- [qwen-image-2](https://affpapa.org/en/nevibecode/skills/qwen-image-2.md) — skill · 240 installs
- [seedream-image](https://affpapa.org/en/nevibecode/skills/seedream-image.md) — skill · 235 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
