← 返回 Skills 市场
MiniMax Vision Skill
作者
gawainchin
· GitHub ↗
· v1.0.1
· MIT-0
94
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install minimax-vision-skill
功能描述
Analyze images using MiniMax CLI (mmx-cli) for vision tasks. Use when user wants image understanding via MiniMax instead of OpenRouter. Triggers on requests...
安全使用建议
This skill is instruction-only and appears coherent: it tells the user how to install and use the MiniMax CLI (mmx) to analyze images. Before installing or running the CLI, verify the mmx-cli npm package (publisher, download counts, source repository), prefer a non-global/local or containerized install to avoid running untrusted code as root, and limit the MiniMax API key scope/rotate it after use. If you do not trust the npm package or the platform.minimax.io domain, do not install the CLI. Otherwise the skill itself does not request unrelated secrets or system access.
功能分析
Type: OpenClaw Skill
Name: minimax-vision-skill
Version: 1.0.1
The skill provides standard instructions for using the MiniMax CLI (mmx-cli) to perform image analysis. It includes legitimate installation commands via npm and authentication steps using the official MiniMax platform. No malicious code, data exfiltration, or suspicious prompt-injection attempts were identified in SKILL.md or _meta.json.
能力标签
能力评估
Purpose & Capability
Name and description match the SKILL.md: the skill directs use of the MiniMax CLI (mmx) for vision tasks. It does not request unrelated credentials, binaries, or config paths.
Instruction Scope
Runtime instructions only describe installing and running the mmx CLI and performing auth with an API key from platform.minimax.io. The instructions do not ask the agent to read unrelated files, environment variables, or send data to unexpected endpoints.
Install Mechanism
This is an instruction-only skill (no install spec). SKILL.md recommends installing mmx-cli via `npm install -g mmx-cli` (or with --prefix). That recommendation is reasonable for a CLI-based integration, but installing third-party npm packages globally can run arbitrary code—users should verify the npm package and prefer local/containerized installs if concerned.
Credentials
The skill declares no required environment variables or primary credential. It instructs the user to run `mmx auth login --api-key <key>` when needed, which is appropriate and proportional for a CLI that requires a service API key.
Persistence & Privilege
always is false and the skill does not request persistent system-level changes. It does not modify other skills' configurations. Autonomous invocation is allowed (platform default) but this skill does not request elevated privileges or broad credential access.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install minimax-vision-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/minimax-vision-skill触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
Fix commands: remove fake dashboard/resources, add correct quota show, trim interactive mode
元数据
常见问题
MiniMax Vision Skill 是什么？
Analyze images using MiniMax CLI (mmx-cli) for vision tasks. Use when user wants image understanding via MiniMax instead of OpenRouter. Triggers on requests... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 94 次。
如何安装 MiniMax Vision Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install minimax-vision-skill」即可一键安装，无需额外配置。
MiniMax Vision Skill 是免费的吗？
是的，MiniMax Vision Skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
MiniMax Vision Skill 支持哪些平台？
MiniMax Vision Skill 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 MiniMax Vision Skill？
由 gawainchin（@gawainchin）开发并维护，当前版本 v1.0.1。
推荐 Skills