← Back to Skills Marketplace
385
Downloads
1
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install mm-music-expert
Description
Create music with MiniMax music models (music-2.5+, music-2.5). Use when generating songs, instrumental tracks, or chanting from lyrics and style prompts via...
Usage Guidance
This skill's code and documentation appear to match the stated purpose (calling the MiniMax music API), but the registry metadata incorrectly lists no required environment variables while both SKILL.md and the Python scripts require MINIMAX_MUSIC_API_KEY. Before installing or granting access:
- Treat MINIMAX_MUSIC_API_KEY as a secret. Only provide it if you trust the MiniMax service and the skill's author. The skill will send prompts/lyrics (user-provided content) to api.minimaxi.com.
- Ask the publisher to correct the metadata to explicitly declare MINIMAX_MUSIC_API_KEY and any runtime dependencies.
- Review the included scripts yourself (or have someone audit them). The code uses the Python 'requests' library and performs network requests to the documented MiniMax endpoint—ensure you are comfortable with that data flow.
- Run the skill in a constrained environment if you want to test it (limited network access, no other secrets present). Confirm there are no other unexpected endpoints or obfuscated code paths.
- If you need to protect sensitive lyrics/content, consider whether sending them to a third-party API is acceptable.
If you cannot verify the publisher or confirm the API's trustworthiness, consider not installing or only using a throwaway API key in a sandbox.
Capability Analysis
Type: OpenClaw Skill
Name: mm-music-expert
Version: 1.0.0
The skill bundle is a well-structured tool for generating music via the MiniMax Music Generation API. The Python scripts (generate_music.py and utils_audio.py) implement standard API interaction, polling, and file handling logic without any evidence of data exfiltration, obfuscation, or unauthorized execution. The SKILL.md file provides a detailed, legitimate interactive workflow for the AI agent to guide users through music creation, and no malicious prompt injection attempts were found.
Capability Assessment
Purpose & Capability
The name/description match the code and API references (MiniMax music generation). However the registry metadata declares no required environment variables or primary credential, while both SKILL.md and the included scripts explicitly require MINIMAX_MUSIC_API_KEY and make network calls to api.minimaxi.com. That mismatch (metadata says 'none' but the skill needs an API key) is an incoherence.
Instruction Scope
SKILL.md defines a tightly-scoped 4-step interactive workflow that only collects musical preferences and constructs prompts/lyrics for the MiniMax API. It instructs use of MINIMAX_MUSIC_API_KEY (necessary for the API). The workflow does not direct the agent to read unrelated system files or exfiltrate data to unexpected endpoints—network activity is limited to the documented MiniMax API. The explicit 'MUST FOLLOW' workflow is restrictive but consistent with the skill's purpose.
Install Mechanism
There is no install spec (instruction-only), but the bundle includes Python scripts. That means nothing will be auto-installed yet code expects runtime dependencies (e.g., Python 'requests') and will perform network I/O. Lack of an install spec or declared dependencies is a packaging inconsistency and may cause runtime surprises, but there's no evidence of downloads from unknown hosts or archive extraction.
Credentials
Registry metadata claims no required env vars, but SKILL.md and scripts expect MINIMAX_MUSIC_API_KEY (Bearer token) and will send user prompts/lyrics to the MiniMax API. Requesting a single API key is proportionate to the stated purpose, but the omission from declared requirements is a red flag: it hides a secret the skill needs. No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It is user-invocable and allows autonomous model invocation (default), which is normal. The skill does not attempt to modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mm-music-expert - After installation, invoke the skill by name or use
/mm-music-expert - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of mm-music-expert skill for creating music with MiniMax Music Generation API.
- Designed an interactive 4-step workflow to guide music novices in producing professional-quality music.
- Includes structured requirement clarification with lettered options for each musical dimension.
- Generates a detailed "Song Blueprint" (section-by-section musical/arrangement plan) before writing prompts and lyrics.
- Prompts and lyrics are derived from the blueprint and include explicit dynamic arc and section tags.
- Provides clear, step-by-step feedback and revision flow for users.
Metadata
Frequently Asked Questions
What is mmMusicExpert?
Create music with MiniMax music models (music-2.5+, music-2.5). Use when generating songs, instrumental tracks, or chanting from lyrics and style prompts via... It is an AI Agent Skill for Claude Code / OpenClaw, with 385 downloads so far.
How do I install mmMusicExpert?
Run "/install mm-music-expert" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is mmMusicExpert free?
Yes, mmMusicExpert is completely free (open-source). You can download, install and use it at no cost.
Which platforms does mmMusicExpert support?
mmMusicExpert is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created mmMusicExpert?
It is built and maintained by Haolan He (@blue-coconut); the current version is v1.0.0.
More Skills