What makes Music Craft — MiniMax notable?

1.1K downloads. Trust evidence available

How should Music Craft — MiniMax be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Music Craft — MiniMax

MiniMax-native music generation for OpenClaw — cover and style transfer that preserves melody, two-song mashups, AI lyrics generation and edit, emotion-driven prompt engineering, and per-flag mmx CLI control over BPM, key, structure, and avoid lists. Extends music-craft with MiniMax Music 2.6 features.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.6.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.6.0release · observed Jul 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171padhas9w52sdjc3110vhss83j8jp:music-craft-minimax

Install using `clawhub skill install s171padhas9w52sdjc3110vhss83j8jp:music-craft-minimax` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/luischarro/music-craft-minimax before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-luischarro-music-craft-minimax/snapshot"

Documentation

CLAWHUB

157,687 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: music-craft-minimax
version: 1.6.0
description: MiniMax-native music generation for OpenClaw — cover and style transfer that preserves melody, two-song mashups, AI lyrics generation and edit, emotion-driven prompt engineering, and per-flag mmx CLI control over BPM, key, structure, and avoid lists. Extends music-craft with MiniMax Music 2.6 features.
metadata: '{"openclaw":{"requires":{"env":["MINIMAX_API_KEY"],"bins":["python3","ffmpeg","mmx"]},"primaryEnv":"MINIMAX_API_KEY","emoji":"\ud83c\udfb6","homepage":"https://github.com/LuisCharro/skills/tree/main/publish/music-craft-minimax","envVars":[{"name":"MINIMAX_API_KEY","required":true,"description":"API key for the MiniMax Music 2.6 token plan. Required for cover, mashup, lyrics generation, and mmx flag control."}]}}'
---
# Music Craft — MiniMax

## What is Music Craft — MiniMax?

Music Craft — MiniMax is the **MiniMax-native power-user upgrade** of [`music-craft`](../music-craft/). It unlocks the features that need the MiniMax Music 2.6 token plan: cover and style transfer that preserves melody, two-song mashups, AI lyrics generation with edit-iter, emotion analysis on input audio, and precise per-flag control over BPM, key, structure, and avoid lists via the `mmx` CLI.

## MiniMax-specific features

- **Cover and style transfer** — preserve the melody of Song X, apply the style of Song Y.
- **Two-song mashup** — Song A's lyrics and emotion + Song B's style, in one output.
- **Lyrics generation API** — `write_full_song` for blank-page or `edit` for revisions, with structure tags.
- **Emotion analysis** — intensity, vocal speed, pitch bends, and 25+ emotion classes drive your prompt.
- **`mmx` per-flag control** — `--bpm`, `--key`, `--structure`, `--vocals`, `--genre`, `--mood`, `--instruments`, `--avoid` as separate flags; prompt and flags lint-checked before generation.
- **Quota-aware batch runs** — 5-hour rolling window check before any cloud batch.

## Why use this instead of music-craft?

Use **music-craft** when you want a structured default that picks the backend for you, or when exact-duration vocal tracks matter. Use **music-craft-minimax** when you need a MiniMax-only feature — cover, mashup, lyrics API, emotion-driven prompting — or when you specifically want `mmx` flag-level control over BPM, key, structure, or an avoid list.

## Quick Start

1. Decide which MiniMax-only feature you need (cover, mashup, lyrics API, emotion analysis).
2. Provide one or two source audio files / lyrics / emotion inputs as the skill requests.
3. The skill picks the right `mmx` flag combination and calls the API.
4. It lints flags + prompt for conflicts, then runs sequentially (one job at a time, never parallel).
5. It verifies duration, file size, and quota headroom before delivering.

## When To Use

Use this skill when the task involves:

- generating a cover of an existing song with a different style (chanson version of a rock track, reggaeton version of a pop hit, and so on). Source must b

README.md

# Music Craft — MiniMax

Advanced music generation for OpenClaw, using the MiniMax Music 2.6 token plan.

Current release: v1.6.0.

This is the **power-user upgrade** of [`music-craft`](../music-craft/). It does everything that skill does, plus the features that require MiniMax:

- Cover and style transfer (preserves melody)
- Two-song mashup (content + style)
- Lyrics generation API
- Emotion-driven prompt engineering
- Fine control via `mmx` CLI (BPM, key, structure, avoid list as separate flags)
- Production helpers: prompt/lyrics linting, retry wrapper, MP3 defaults, lyrics-alignment verification, and loudness finalization

Cloud generation is for speed and MiniMax-native workflows, not exact duration.
The 2026-06-12 field run saved 18/18 cloud outputs, but durations ranged from
57-135% of requested length. Use [`music-craft`](../music-craft/) with local
ACE-Step when exact duration matters.

## Data and consent

This skill may send prompts, lyrics, reference audio, and cover/mashup inputs to MiniMax when the user chooses cloud generation. Audio input must be a **local file path** — URLs are not accepted in v1.5.0+. Use the private `music-source-fetch` skill to fetch audio by title first. There is no image, face, OCR, or VLM pipeline.

## Licensing and commercial use

ClawHub publishes this skill bundle under MIT-0, so the skill instructions and
bundled helper code may be used, modified, and redistributed commercially
without attribution. That does not grant MiniMax rights or rights to the
inputs or outputs. Each operator must use their own MiniMax account/API key
and accept the current terms for the exact API/Token Plan product. The API/Open Platform and
consumer web/app terms are separate; a subscription or third-party claim of
“commercial use” is not enough to establish the rights for this CLI/API
workflow. Verify the applicable terms before commercial release. Inputs must
be owned or properly licensed, and generated audio is not guaranteed to have
exclusive copyright protection in every jurisdiction.

## When to use

Use this skill when the task involves:

- cover or style transfer from a local reference audio file (URLs not accepted; use `music-source-fetch` to fetch by title)
- two-song mashup
- lyrics generation via the MiniMax API
- emotion analysis on input audio
- fine parameter control via `mmx` CLI
- fast standard cloud iterations where approximate duration is acceptable

Stay in [`music-craft`](../music-craft/) when the user only needs standard song generation, a text-only style reference without melody preservation, or provider-agnostic prompting. Use MiniMax when the request uses a local reference audio file, needs cover/mashup, lyrics API iteration, emotion-driven prompting, or exact `mmx` flags.

## First Response

- **Cover from local audio**: default to the one-step cover path; ask only if the user wants translated lyrics, edited ASR lyrics, or new lyrics.
- **Style transfer only**: do not use cover unless the melody must s

_meta.json

{
  "ownerId": "kn7fkh362pnj2zckq8pcxfaxr9821zv8",
  "slug": "music-craft-minimax",
  "version": "1.6.0",
  "publishedAt": 1785411554548
}

references/advanced-audio-analysis.md

# Advanced Audio Analysis with Free Tools

The base emotion analysis in [`emotion-analysis.md`](emotion-analysis.md) uses `librosa` + `parselmouth` (Praat) + `scipy` to extract per-section features. Those cover the core 30 emotions. This file covers **advanced free tools** that go deeper: more accurate pitch, source separation, note transcription, music theory, and pre-trained emotion / genre / mood classifiers.

All tools listed here are **open source** (BSD, MIT, Apache, or GPL). All can be installed via `pip` (some need system dependencies like `ffmpeg`). They are **optional** — the base skill works without them. Install only what you need.

---

## Currently Implemented Advanced Features (v0.1.0)

The following advanced analysis features **are now implemented** in the MiniMax layer. Each is available as an optional dependency and is used in the prompt pipeline to enrich generation prompts with precise audio characteristics.

| Feature | Library | What it detects | Pip package |
|---|---|---|---|
| **tempogram_ratio** | librosa | Swing / groove feel ( eighth-note swing ratio ) | `librosa` (already in base) |
| **tonnetz** | librosa | Tonal harmony quality — diatonic/chromatic, consonant/dissonant | `librosa` (already in base) |
| **spectral_contrast** | librosa | Valley-to-peak energy ratio per frequency band (timbre) | `librosa` (already in base) |
| **HPSS** | librosa.effects.hpss | Harmonic-percussive source separation | `librosa` (already in base) |
| **Formant analysis** | parselmouth | Vocal register detection — chest / head / falsetto | `parselmouth` (already in base) |
| **HNR** | parselmouth | Harmonics-to-noise ratio — breathiness vs clarity | `parselmouth` (already in base) |
| **Jitter / Shimmer** | parselmouth | Microperturbations in pitch and amplitude — voice stability | `parselmouth` (already in base) |
| **LUFS / LRA** | pyloudnorm | Perceptual loudness (integrated LUFS) and loudness range (LRA) | `pyloudnorm` |
| **Chord progression** | autochord | Automatic chord symbol extraction | `autochord` |
| **Song structure** | allin1 | Neural structure segmentation — intro / verse / chorus / bridge / outro | `allin1` |
| **CLAP classification** | transformers | Zero-shot genre / mood / instrument / era classification | `transformers` |

### tempogram_ratio (librosa)

Detects swing and groove by measuring the deviation of note onsets from a perfectly regular grid. A ratio near 1.0 is straight; above ~1.2 indicates a noticeable swing feel.

**Pipeline use**: When the user wants "groovy" or "laid-back" output, `tempogram_ratio` quantifies the swing intensity to pass a precise BPM/swing hint to `mmx`.

```python
import librosa

y, sr = librosa.load('/tmp/song.wav')
tempo, beats = librosa.beat.beat_track(y=y, sr=sr)
oenv = librosa.onset.onset_strength(y=y, sr=sr, feature_mode='spectral')
tempogram = librosa.feature.tempogram(oenv=oenv, sr=sr)
# Ratio of beat-strength deviations indicates swing
```

### tonnetz (librosa)

Computes the ton

references/changelog.md

# Changelog

Release history for music-craft-minimax. Operating guidance lives in the
topic references; this file is history only.
# v1.6.0

- Reordered `SKILL.md` for discoverability: added hero sections
  ("What is Music Craft — MiniMax?", "MiniMax-specific features",
  "Why use this instead of music-craft?", "Quick Start") at the top
  of the body. MiniMax-only features (cover, mashup, lyrics API,
  emotion-driven prompting, `mmx` flag control, quota-aware batches)
  are now the first thing a visitor reads.
- Moved the licensing and commercial-use gate to the end of `SKILL.md`
  (preserving all legal content verbatim, including the "Cloud duration
  is approximate" routing warning); data / consent sits just above it.
- Updated the frontmatter `description:` to anchor-keyword pack
  (cover and style transfer, two-song mashup, lyrics generation API,
  emotion-driven prompt engineering, mmx CLI, Extends music-craft)
  for clearer ClawHub routing.
- Removed the old "Quick Start with the Orchestrator" section; the
  new hero "Quick Start" supersedes it.
- No behaviour, no env vars, no bins — pure content reordering and
  versioning.



# v1.5.1

- Added a licensing and commercial-use gate for MiniMax API/CLI workflows.
- Clarified the difference between MiniMax Open Platform/API terms and
  consumer app/web terms.
- Required each operator to use their own account/API key and verify current
  product-specific commercial-use terms before release.

## v1.5.0

v1.5.0 is a **breaking change** that isolates all internet-download code
into the new private `music-source-fetch` skill and removes the album-art
/ face / OCR / VLM image pipeline entirely. The published skill is now
audio-only and accepts only local file paths.

**Removed (moved to `publish/music-source-fetch/`):**
- `scripts/download_youtube.py`, `scripts/download_mx3.py`,
  `scripts/fetch_lyrics_web.py`, `scripts/audio_sources.py`
- `analysis_orchestrator.py` flags: `--youtube`, `--audio-url`,
  `--lyrics-source {web,auto}`
- LRCLib web lyrics lookup; Whisper on the local file is the only lyrics
  source

**Deleted entirely (no replacement):**
- `scripts/analyze_image.py`, `scripts/extract_video_features.py`
- `analysis_orchestrator.py` flags: `--image`, `--video`, `--vlm`,
  `--ocr`, `--faces`
- Album-art color palette, face detection, OCR, VLM captioning flows

**Changed:**
- `check_environment.py` no longer recommends `yt-dlp`; drops `cv2`/`PIL`
  from optional imports
- `lint_music_request.py` URL detection now emits a `url_not_accepted`
  warning and routes to `needs_clarification`; only local file paths
  route to `minimax_cover`
- SKILL.md "Audio Source Fallback Order" replaced with "Audio Source
  (Local Only)"
- `cover-workflow.md` and `mashup-workflow.md` add explicit cloud
  transmission consent paragraphs (audit SQP-2)
- `examples.md` neutralises hardcoded language/locale defaults (audit SQP-3)
- README narrows the auto-load trigger (audit SQP-1)
- Frontmatter `metadata.openclaw.r

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.