MiniMax-H3-Image Prompt Writing skill
The skill turns a short idea into a full MiniMax-H3-Image prompt and can render the picture through the MiniMax API.
- 312 ★ on the repository
- Last commit
Extended access
Why this level
- The `generate.py` script sends the prompt text and references to the MiniMax API with your key.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/minimax-h3-image-prompt-writingDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The `generate.py` script sends the prompt text and references to the MiniMax API with your key.
This is third-party code. Review the repository files before installing.
What it does
The `h3-image-prompt-writing` skill lives in the official repository of the open-weight MiniMax-H3-Image model. It takes an idea, a brief or reference images and writes a detailed description of the whole image: purpose, layout, aspect ratio, subjects, style and every word of text on it. For edits the skill numbers up to 16 references as `<Picture 1>`, `<Picture 2>`. The `scripts/generate.py` script sends the prompt to the MiniMax API when `MINIMAX_API_KEY` is set. Without a key the agent returns the prompt alone. Guides for text in images and for editing sit in `references/`.
Who it is for. Designers and marketers making posters, infographics and scenes in MiniMax-H3-Image who do not want to craft prompts by hand.
Good fit when
- A 3:4 poster with a Chinese title and exact text placement is needed.
- A short idea must become a detailed prompt for an infographic with exact values.
- Several photos are combined into one scene and references are named in order.
- An existing prompt is improved and rendered at once through `generate.py`.
Not a fit when
- You work with an image model other than MiniMax-H3-Image.
- You want to run the weights locally with no API calls.
- You need video, not an image.
Example request
Use h3-image-prompt-writing to make a 3:4 poster of a night market in the rain, titled "雨夜集市", and render it.Limitations
Rendering needs `MINIMAX_API_KEY`, and on the China platform also `MINIMAX_API_BASE=https://api.minimax.cn`. The API always expands editing prompts itself, so `generate.py` sends as written only text-to-image prompts. The guides in `references/` are in English. Running the weights yourself follows the main model README; the skill does not do that. Image quality depends on the model and your key plan; the skill is responsible only for the prompt text.
How to disable. Delete the `h3-image-prompt-writing` folder from the agent skills directory. Remove `MINIMAX_API_KEY` from the environment.
FAQ
How do I install only this skill?
With `npx skills add https://github.com/MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing`. The `--list` flag shows every skill in the repository.
What happens without an API key?
The agent returns a finished prompt and says that with `MINIMAX_API_KEY` the skill can render the picture itself.
How many references are supported?
Up to 16. The prompt names them `<Picture 1>`, `<Picture 2>` and so on in the order supplied.
How do I specify text on the image?
Quote every word in its own language and give position, size and line breaks. When there is no text, the prompt states that the image has no letters or numbers.
Which agents fit?
Any agent that reads `SKILL.md`: Claude Code, Codex, Cursor. The skill folder also has `agents/openai.yaml` for Codex.
Discussion
No questions or reviews yet.
Related
SkillsThe skill retells a reference video, waits for your confirmation and writes MiniMax H3 prompts per scene and shot.
A MiniMax skill that turns a short song description and tagged lyrics into a detailed prompt for the MiniMax Music 3 generator
Three Codex and Claude Code skills: search MiniMax H3 cases and full prompts, pick tutorial routes and prepare submissions
Codex skill that makes short MiniMax H3 videos from your images on a Google Colab GPU, with a job queue and result download
Nano Banana Pro Prompts Recommend
AI Image Prompt Recommender
A skill that picks ready image-generation prompts from a large library, shows sample images and assembles a prompt for your text
The official mmx CLI of the MiniMax platform with an agent skill: text, images, video, speech, audio transcription, vision and search
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| MiniMax-H3-Image Prompt Writing (this card) | no | 312 | |
| MiniMax Skills | yes | 13,827 | general MiniMax skills; this is one skill for the H3 image model with text and editing rules |
| AI Image Prompts | no | 1,377 | a prompt set for various models; this skill writes prompts for MiniMax-H3-Image specifically and can render |
README in short
The skill follows the model's official Prompting Tips and sits in the repository `skills/` directory. It installs through the skills CLI.
README badge
Original SKILL.md
---
name: h3-image-prompt-writing
description: Write prompts for MiniMax-H3-Image text-to-image generation and image editing, and optionally render them through the MiniMax API. Use when the user wants an image such as a poster, infographic, chart, product shot, UI screen, character, scene, storyboard or grid, wants to improve an image prompt, or wants to edit, combine or restyle reference images with MiniMax-H3-Image.
---
# MiniMax-H3-Image Prompt Writing
MiniMax-H3-Image renders best from a complete description of the finished image: what the image is
for, what is in it and where, how it looks, and every word that appears on it. This skill turns a
short request into that description, for text-to-image and for editing with up to 16 reference
images, and can send the result to the MiniMax API.
## Workflow
1. **Pick the task.** Use text-to-image when there are no input images. Use editing when the user
supplies images to change, combine or borrow from. Read the matching guide and its examples
before writing:
- [references/t2i-en.txt](references/t2i-en.txt) for text-to-image.
- [references/edit-en.txt](references/edit-en.txt) for editing. Look at every input image, in
the order supplied.
2. **Plan the image** in this order: purpose and deliverable, overall layout, aspect ratio, the
subjects and what they are doing, the visual style, the text. Fill ordinary gaps yourself; a
short idea is enough. Write requested copy yourself, mark example data as illustrative and keep
an unseen asset as a named reference. Ask only when a missing fact would make the prompt wrong,
such as a chart of the user's own figures with none given.
3. **Write the prompt** with the rules below and the guide.
4. **Check it** against the request with the [final check](#final-check).
5. **Deliver** it in the [output format](#output-format). When the user asks for the image itself,
[render it](#rendering-the-prompt). If `MINIMAX_API_KEY` is not set, deliver the prompt and say
that setting the key lets the skill render it.
## Writing rules
### Basic description
- **Task before style.** Open with what the image is and what it is for, then the main people or
objects and their state or action. Style comes after.
- **Layout before details.** Give the number of subjects, their positions, the viewpoint and the
empty space. For dense content, name the regions first and then fill each one: "a title across
the top; below it, a photo on the left and three short paragraphs on the right."
- **Style through visible details.** Write color, material, light and texture, such as "soft side
light, brushed-metal reflections, generous white space", instead of words like "premium" or
"high-end". Keep the details that matter and drop contradictory ones.
### Text and information