← Back to Skills Marketplace
Minimax Image
by
LilMrmeeseeks
· GitHub ↗
· v1.1.0
· MIT-0
104
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install openclaw-minimax-img
Description
Generate images using MiniMax API (image-01 model). Automatically optimizes prompts for better results. Use when user asks to generate images, create picture...
Usage Guidance
This skill's code does what its description claims (optimizes prompts and calls an external image API), but the package/registry metadata and file manifests are inconsistent. Before installing: 1) Verify you trust the API host (https://api.minimaxi.com) and the origin of this skill; 2) Only provide an API key if you understand its scope and trust the service — the skill will send your prompt text to that endpoint; 3) Expect to need Node and to install dependencies (axios) since package.json is present but no install step is declared; 4) Note the registry metadata lists no required env vars while SKILL.md and index.js require MINIMAX_API_KEY or AIMLAPI_API_KEY — ask the publisher to fix the manifest/version mismatches (package.json/_meta.json vs SKILL.md/registry) before trusting automatic installs. If you cannot verify the provider or publisher, do not supply sensitive or reuse API keys.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-minimax-img
Version: 1.1.0
The skill bundle is a legitimate implementation for generating images via the MiniMax API. The code in index.js correctly handles API keys from environment variables, performs basic prompt optimization (mapping Chinese keywords to English), and makes standard HTTP requests to the official MiniMax endpoint (api.minimaxi.com). No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The code (index.js) implements prompt optimization and calls an external image-generation API (model image-01) which is consistent with the skill name/description. The dependency (axios) is reasonable for HTTP calls. However, the registry metadata claims no required env vars while SKILL.md and the code require an API key, an inconsistency that reduces trust in the manifest.
Instruction Scope
SKILL.md instructs the agent to use MINIMAX_API_KEY or AIMLAPI_API_KEY and to call https://api.minimaxi.com/v1/image_generation; the runtime code follows that. The instructions do not request other files or broad system data. The concern is that the skill metadata does not declare the required env vars (so the skill may fail or prompt users unexpectedly), and the SKILL.md is the authoritative runtime instruction but is out of sync with the registry metadata.
Install Mechanism
There is no install spec (instruction-only install), which is lower risk. But the package includes code and package.json/package-lock.json with dependencies (axios). That implies the runtime environment must provide Node and install dependencies; the lack of an explicit install specification is an operational mismatch (not inherently malicious) and could cause surprises if dependencies are not installed automatically.
Credentials
The code requires a single API credential (MINIMAX_API_KEY or AIMLAPI_API_KEY), which is proportional for a third-party API. The problem is the registry metadata declares no required env vars/primary credential, creating a mismatch. Also confirm what provider 'minimaxi.com' is and whether the API key you provide is scoped appropriately — the skill will send prompts and any returned URLs to that external service.
Persistence & Privilege
The skill does not request permanent presence (always: false). It does not modify other skills or system configs. Autonomous invocation is allowed by default but not combined with other high-risk flags here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-minimax-img - After installation, invoke the skill by name or use
/openclaw-minimax-img - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
**MiniMax Image Generator v1.1.0 introduces automatic prompt optimization for improved image generation results.**
- Automatically converts user input to concise, clear English prompts for image generation.
- Optimizes prompts with relevant keywords for better style, lighting, and quality.
- Supports direct user commands in Chinese or English.
- Uses 'image-01' model via MiniMax API with a 16:9 aspect ratio by default.
Metadata
Frequently Asked Questions
What is Minimax Image?
Generate images using MiniMax API (image-01 model). Automatically optimizes prompts for better results. Use when user asks to generate images, create picture... It is an AI Agent Skill for Claude Code / OpenClaw, with 104 downloads so far.
How do I install Minimax Image?
Run "/install openclaw-minimax-img" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Minimax Image free?
Yes, Minimax Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Minimax Image support?
Minimax Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Minimax Image?
It is built and maintained by LilMrmeeseeks (@lilmrmeeseeks); the current version is v1.1.0.
More Skills