← 返回 Skills 市场
83
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mmx
功能描述
Multimodal content generation and analysis via MiniMax CLI, including text chat, image/video creation, speech synthesis, music, vision, and web search with A...
安全使用建议
This skill is a CLI usage guide for a third-party 'mmx' tool. Before installing/using it: 1) Verify the origin and integrity of the mmx CLI (source URL or package repo), because the skill assumes that binary is installed and trustworthy. 2) Expect to provide an mmx API key — confirm how that key is stored/used; the skill did not declare any environment variable for it. 3) Note the examples call other local binaries (mpv, jq, cat); ensure you have or trust those tools before piping data to them. 4) Ask the skill author or publisher for a homepage/source repository and an explicit list of required binaries and credentials; absence of those details is the main inconsistency. 5) If you will run commands from this skill, run them in a controlled environment (sandbox/container) until you've validated the CLI and API endpoints.
功能分析
Type: OpenClaw Skill
Name: mmx
Version: 1.0.0
The 'mmx' skill bundle provides a standard interface for the MiniMax multimodal CLI, enabling text, image, video, and audio generation. The instructions in SKILL.md are well-documented and align with the legitimate use of the mmx tool, with no evidence of malicious intent, data exfiltration, or prompt injection attacks.
能力评估
Purpose & Capability
The SKILL.md describes a CLI-centric multimodal tool (mmx) and the commands in the file line up with that purpose. However the registry metadata provided with the skill claims no required binaries or credentials while the SKILL.md frontmatter and content explicitly expect the 'mmx' executable and an API key. This discrepancy between declared requirements and the instructions is inconsistent.
Instruction Scope
Runtime instructions tell the agent to run many mmx CLI commands and to perform authentication via 'mmx auth login --api-key <your-api-key>'. The docs also demonstrate piping to other system tools (mpv, jq, cat) and use of local files/URLs. Those auxiliary binaries and the need to supply an API key are not declared elsewhere; the instructions therefore reference system state and tools outside the skill's declared surface.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which minimizes installer risk. Nothing in the package attempts to download or execute external code by itself.
Credentials
The SKILL.md requires an API key for 'mmx auth login' but the skill does not declare any required environment variables or primary credential in the registry metadata. That omission means the skill's credential needs are not made explicit. Additionally, commands reference other local tools (mpv, jq) which might require additional permissions or environment setup; those are not declared either.
Persistence & Privilege
The skill is not marked always:true and is user-invocable; it does not request persistent presence or claim privileges to alter other skills or system-wide settings. No install actions are present that would grant it additional persistence.
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 mmx - 安装完成后，直接呼叫该 Skill 的名称或使用
/mmx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
v1.0.0
Initial release: full MiniMax multimodal CLI reference - text, image, video, speech, music, vision generation
元数据
常见问题
Mmx 是什么？
Multimodal content generation and analysis via MiniMax CLI, including text chat, image/video creation, speech synthesis, music, vision, and web search with A... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 83 次。
如何安装 Mmx？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mmx」即可一键安装，无需额外配置。
Mmx 是免费的吗？
是的，Mmx 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Mmx 支持哪些平台？
Mmx 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 Mmx？
由 ariffazil（@ariffazil）开发并维护，当前版本 v1.0.0。
推荐 Skills