A comprehensive command-line interface for AI agents to access MiniMax's full suite of multimodal capabilities including video, audio, and image generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install minimax-mmx
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install minimax-mmx using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is MiniMax MMX-CLI?
MiniMax MMX-CLI is a professional-grade developer tool designed to empower AI agents with multimodal intelligence. By integrating this skill into Openclaw Skills, developers gain access to high-fidelity image generation, professional video production (via Hailuo models), and lifelike speech synthesis. It acts as a bridge between the command line and the MiniMax ecosystem, providing streamlined access to cutting-edge generative AI.
This skill is particularly optimized for non-interactive environments and automated workflows. It allows agents to not only generate creative assets but also perform advanced image understanding, web searching, and music composition, making it a versatile addition to any AI-driven development stack.
MiniMax MMX-CLI Use Cases
- Automating the generation of high-quality marketing images and videos via AI agent prompts.
- Integrating realistic speech synthesis and custom music creation into multimedia applications.
- Enabling AI agents to perform visual analysis and web research to ground their responses in real-time data.
- Building automated asset pipelines that utilize Openclaw Skills for consistent character and style generation.
How MiniMax MMX-CLI Works
- The AI agent initiates a request by calling specific MMX-CLI commands with required parameters like prompts or file paths.
- For creative tasks like video generation, the tool supports asynchronous execution to handle long-running processes without blocking the agent.
- The CLI communicates with MiniMax APIs to process the request, using advanced models like speech-hd or image-01.
- Resulting files (MP3, MP4, PNG) are saved to the local filesystem, while metadata is returned in structured JSON for the agent to parse.
- Status codes and quiet modes ensure that the integration remains stable and clean within automated logs.
MiniMax MMX-CLI Setup
To start using this tool with Openclaw Skills, install the CLI globally and authenticate with your API key:
npm install -g mmx-cli
mmx auth login --api-key <your-api-key>
You can verify your connection and check available credits using:
mmx quota show
MiniMax MMX-CLI Data Schema & Taxonomy
The skill manages structured data outputs to ensure compatibility with automated pipelines. Use the --output json flag to receive structured metadata.
| Feature | Output Type | Description |
|---|---|---|
| Image Generation | .png / .jpg | Visual assets with optional subject reference consistency. |
| Video Generation | .mp4 | High-definition video clips (up to 6s) with task ID tracking. |
| Speech & Music | .mp3 | High-fidelity audio files for narration or background music. |
| Vision & Search | JSON | Structured text analysis or web search results for agent context. |
MiniMax MMX-CLI Advanced Features
- Asynchronous task management for video generation allowing agents to query status and download results later.
- Agent-optimized flags including
--quiet,--output json, and--non-interactiveto prevent parsing errors. - Subject Consistency Reference (
--subject-ref) to maintain character visual identity across multiple image generations. - Multi-model support covering everything from basic text chat to complex image understanding and web-scale searching.
SKILL.md
Loading
Related Openclaw Skills
Bias Audit
A disciplined decision-framing agent skill designed to surface cognitive biases and neutralize emotionally slanted requests before they harden into flawed decisions.
Frustration Translator
A sophisticated tool designed to detect emotional charge in user prompts and translate them into clear, actionable technical instructions for AI agents.
Rate Limit Guard
A protective layer for AI agents that prevents 429 rate limit loops and optimizes token usage during API failures.
Podcast Digest
An advanced AI tool that converts podcast audio and transcripts into structured knowledge assets, interactive visual reports, and cross-episode matrices.
Pilot GitHub Bridge
A bridge that translates GitHub webhook events into actionable Pilot Protocol messages for autonomous agents.
pilot-gossip
A decentralized protocol for achieving eventually-consistent state replication across AI agent swarms using epidemic-style communication.
Featured*
