← Back to Skills Marketplace
1421
Downloads
0
Stars
12
Active Installs
1
Versions
Install in OpenClaw
/install minimax-image-generation
Description
MiniMax AI图片生成，支持 image-01 和 image-01-live 模型。 image-01: 画面表现细腻，支持文生图、图生图 image-01-live: 手绘、卡通等画风增强，支持文生图并进行画风设置 需要 MiniMax API Key (Coding Plan)。
Usage Guidance
This skill appears to do what it claims: a simple Python client for MiniMax image generation that needs your MiniMax API key. Before installing: (1) Confirm you trust the MiniMax endpoint (api.minimaxi.com) and that your API key is a scoped key (not a broadly privileged secret). (2) Be aware returned image URLs expire (SKILL.md says 24 hours). (3) The repository source is 'unknown' and has no homepage—if you require provenance, request a published source or vendor link. (4) Install only within an environment where storing MINIMAX_API_KEY as an env var is acceptable (avoid putting long-lived secrets in shared CI logs). (5) Note the minor metadata mismatch: _meta.json lists curl though the script uses Python requests; this is low risk but worth noting.
Capability Analysis
Type: OpenClaw Skill
Name: minimax-image-generation
Version: 1.0.0
The skill is a legitimate implementation for generating images via the MiniMax AI API. The core script, `scripts/minimax_image_create.py`, correctly handles API requests to the official endpoint (api.minimaxi.com), implements standard authentication using environment variables, and includes thorough input validation for parameters like aspect ratios and image dimensions. No indicators of data exfiltration, malicious execution, or harmful prompt instructions were identified.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, _meta.json, and the script all describe and implement an image-generation client for MiniMax using the same API host (api.minimaxi.com) and the expected MINIMAX_API_KEY. The required functionality (text->image and image->image) is implemented and matches the documented models and options.
Instruction Scope
Runtime instructions only direct the agent/user to set MINIMAX_API_KEY, invoke the provided Python script, and call the documented API endpoint. The SKILL.md and script do not attempt to read unrelated files, other environment variables, or send data to third-party endpoints beyond the stated MiniMax API.
Install Mechanism
There is no install spec (instruction-only + a bundled script). requirements.txt only lists 'requests'. _meta.json lists python3 and curl, but the bundled script uses Python 'requests' (curl is not used). This mismatch is minor but worth noting; there are no downloads from untrusted URLs or extraction of archives.
Credentials
The only credential required is MINIMAX_API_KEY (declared as primaryEnv). No other tokens, secrets, or unrelated credentials are requested. This is proportionate for a hosted image-generation API client.
Persistence & Privilege
always is false and the skill does not request system-wide persistence or modification of other skills. It is user-invocable and uses the normal autonomous-invocation default; nothing else grants elevated or permanent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install minimax-image-generation - After installation, invoke the skill by name or use
/minimax-image-generation - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of MiniMax Image Generation:
- Supports image generation using MiniMax's image-01 and image-01-live models via Coding Plan API.
- Enables both text-to-image and image-to-image generation with multiple aspect ratios.
- Provides optional style settings for image-01-live, including cartoon, watercolor, and more.
- Offers a command-line interface with various configurable parameters (model, aspect ratio, output format, etc.).
- Requires a MiniMax API Key; supports batch generation and output in URL or base64 format.
- Includes examples and detailed parameter documentation.
Metadata
Frequently Asked Questions
What is minimax-image?
MiniMax AI图片生成，支持 image-01 和 image-01-live 模型。 image-01: 画面表现细腻，支持文生图、图生图 image-01-live: 手绘、卡通等画风增强，支持文生图并进行画风设置 需要 MiniMax API Key (Coding Plan)。 It is an AI Agent Skill for Claude Code / OpenClaw, with 1421 downloads so far.
How do I install minimax-image?
Run "/install minimax-image-generation" 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 wanycun (@wanycun); the current version is v1.0.0.
More Skills