feiskyerfeiskyer/codex-settings/skills/minimax-image-skill/SKILL.md

minimax-image-skill

Skill248 starsChanged 4 months agoMITView on GitHub

Generate images when the user names MiniMax or image-01/image-01-live. Use the default image skill when no provider is named.

Reads credentials

In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brainstormingSkill
- claude-skillSkill
- code-simplifierSkill
- deep-researchSkill
- github-fix-issueSkill
- github-review-prSkill
- gpt-image-skillSkill
- grill-meSkill
- handoffSkill
- nanobanana-skillSkill
- youtube-transcribe-skillSkill

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Use Python 3.9 or newer. The helper uses only the Python standard library.
line 17
Distinctive:
Every option has a working default, so pass only what the request actually constrains:
line 21
Very specific:
Use --model image-01-live when requested.
line 38
Distinctive:
Never print or persist the API key.
line 44
Distinctive:
Do not call the API until the prompt and local output path pass validation.
line 45
Distinctive:
If the API rejects a field combination, correct an assistant-chosen option when the user's requested result is unchanged.
line 46
Distinctive:
Do not claim success unless at least one image was saved locally.
line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

MiniMax Image Skill

Generate images from a text prompt through the bundled MiniMax Image API helper.

Resolve the skill directory

Resolve the absolute directory containing this SKILL.md before running a command and refer to it as <skill-dir>. Keep output paths relative to the user's working directory unless the user requests another location.

Requirements

Export MINIMAX_API_KEY before running the helper.
Use Python 3.9 or newer. The helper uses only the Python standard library.

Generate an image

Every option has a working default, so pass only what the request actually constrains:

python3 "<skill-dir>/minimax_image.py" \
  --prompt "A quiet observatory beneath an aurora" \
  --output "observatory.png"

The global endpoint is used by default. Select the China endpoint explicitly when needed:

python3 "<skill-dir>/minimax_image.py" \
  --region china \
  --prompt "A paper-cut landscape at sunrise" \
  --output "landscape.png"

Use --model image-01-live when requested. Consult python3 "<skill-dir>/minimax_image.py" --help for optional fields and accepted values.

The helper downloads URL responses immediately because generated URLs expire. It also decodes base64 responses and creates output parent directories automatically. For multiple results, it adds a numeric suffix to the output filename.

Safety and failures

Never print or persist the API key.
Do not call the API until the prompt and local output path pass validation.
If the API rejects a field combination, correct an assistant-chosen option when the user's requested result is unchanged; ask when resolving it would change a user constraint. Check for generated output before a bounded retry.
Do not claim success unless at least one image was saved locally.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free