A comprehensive multimodal interface for generating and analyzing text, images, video, speech, and music via the MiniMax CLI.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install 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 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 MMX: MiniMax Multimodal CLI?
MMX is a versatile integration for Openclaw Skills that brings the full power of MiniMax's multimodal capabilities to your development environment. It serves as a unified command-line interface for complex generative tasks, ranging from high-speed text chat and vision analysis to sophisticated video synthesis and music composition.
This skill is designed for creators and developers who need to bridge the gap between different media formats. Whether you are generating 16:9 assets for a presentation or synthesizing speech with specific vocal textures, MMX provides a streamlined workflow to execute these tasks without leaving the terminal.
MMX: MiniMax Multimodal CLI Use Cases
- Rapid generation of high-fidelity images with specific aspect ratios for visual projects.
- Creating AI-synthesized video clips from text prompts with asynchronous tracking.
- Composing original music tracks with auto-generated lyrics or instrumental arrangements.
- Converting technical documentation or messages into natural-sounding speech for accessibility.
- Performing vision-based analysis on local files or URLs to describe contents or identify objects.
How MMX: MiniMax Multimodal CLI Works
- The user initializes the skill by verifying authentication status using the mmx auth commands.
- When a multimodal request is made, the skill routes the prompt to the specific MiniMax engine (Text, Image, Video, Speech, or Music).
- For asynchronous tasks like video generation, the skill initiates a task ID for progress monitoring.
- Generated assets are processed and saved to specified local directories or piped to external players like mpv.
- Users can check quotas and adjust regional configurations directly through the utility subcommands.
MMX: MiniMax Multimodal CLI Setup
To integrate this into your Openclaw Skills library, ensure the mmx binary is installed and authenticated:
# Authenticate with your API key
mmx auth login --api-key <your-api-key>
# Verify your configuration and region
mmx config show
# Ensure the CLI is up to date
mmx update latest
MMX: MiniMax Multimodal CLI Data Schema & Taxonomy
The skill manages various output formats and metadata based on the media type generated:
| Data Type | File Formats | Primary Metadata |
|---|---|---|
| Text | JSON, Plain Text | Model ID, Role (System/Assistant) |
| Images | PNG, JPG | Aspect Ratio, Prompt Seed |
| Video | MP4 | Task ID, File ID, Status |
| Audio | MP3 | Voice ID, Speed, Lyrics |
| Vision | JSON, String | Image URL/Path, Description |
MMX: MiniMax Multimodal CLI Advanced Features
- Multi-turn conversation support for complex, context-aware text generation.
- Lyrics optimization for music generation that automatically crafts verses based on mood prompts.
- Streaming TTS output allowing for real-time audio playback through system pipes.
- Music cover generation using reference audio files or URLs to restyle existing tracks.
- Structured search capabilities that return web-verified facts in parseable JSON format.
SKILL.md
Loading
Related Openclaw Skills
GEOX Ground
A specialized reasoning layer for AI agents that enforces rigorous physics-based grounding and epistemic clarity in Earth sciences and subsurface data analysis.
arifOS-sense
arifOS-sense serves as the non-negotiable constitutional governance kernel for AI agents, managing the decision boundary for high-stakes and irreversible actions.
Lyria 3 Pro AI Music Generator
A professional-grade AI music generation tool powered by Google's Lyria 3 Pro model for creating structured tracks from text prompts.
Wan 2.7 Image
A free, open-source AI text-to-image generator powered by Alibaba's Wan 2.7 model that requires no account or signup.
MMX Text Researcher
A high-performance deep research skill leveraging the MiniMax CLI for multi-source synthesis and structured investigation.
Ecommerce Sustainability Advisor
An operational heuristic tool that generates phased sustainability action plans and green-claim risk assessments for e-commerce brands.
Featured*
