claude-music-analyze
Analyzes audio files for BPM, musical key, loudness (LUFS), duration, format, and quality metrics. Uses ffprobe for metadata and…
Quick random music generation with smart genre defaults. Picks a random genre, crafts an appropriate caption, and generates with draft quality for fast exploration.
$ npx -y skills add AgriciDaniel/claude-music --skill claude-music-random --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/claude-music-randomContext preview
The summary Claude sees to decide when to auto-load this skill.
Quick random music generation with smart genre defaults. Picks a random genre, crafts an appropriate caption, and generates with draft quality for fast exploration.
name: claude-music-random description: > Quick random music generation with smart genre defaults. Picks a random genre, crafts an appropriate caption, and generates with draft quality for fast exploration. when_to_use: > Use when user says "random", "surprise me", "quick song", "random music", or wants to explore without specific requirements. model: haiku allowed-tools: - Bash - Read
**User**: "surprise me"
**Claude picks**: Lo-fi (from the pool below), composes a caption.
**Command**:
bash ~/.claude/skills/claude-music/scripts/music_engine.sh \ --quality draft \ generate \ --caption "lo-fi hip-hop, chill, atmospheric, vinyl crackle, mellow piano" \ --instrumental --duration 60
**Expected JSON on stdout** (batch=4 from draft preset):
{
"success": true,
"task_type": "text2music",
"model": "acestep-v15-turbo",
"outputs": [
{"path": ".../text2music_20260416_121530_01.flac", "seed": 81, "index": 1},
{"path": ".../text2music_20260416_121530_02.flac", "seed": 84012, "index": 2},
{"path": ".../text2music_20260416_121530_03.flac", "seed": 44190, "index": 3},
{"path": ".../text2music_20260416_121530_04.flac", "seed": 2031, "index": 4}
],
"timing": {"generation_sec": 14.8},
"count": 4
}Then present all four paths and ask which to iterate on.
1. Pick a random genre from the list below 2. Craft a caption using genre-appropriate tags 3. Generate with draft quality (4 variants, ~15s)
Pick randomly from: Pop, Rock, Jazz, Lo-fi, Electronic, Hip-hop, R&B, Ambient, Folk, Synthwave, Bossa Nova, Afrobeat, Funk, Soul, Blues, Country, Reggae, Classical Piano, Cinematic, Chillwave, House, DnB, Trap, Phonk
# Instrumental random (fastest) bash ~/.claude/skills/claude-music/scripts/music_engine.sh generate \ --caption "<genre tags here>" \ --instrumental --quality draft --duration 60 # With vocals (Claude writes a quick verse + chorus) bash ~/.claude/skills/claude-music/scripts/music_engine.sh generate \ --caption "<genre tags>" \ --lyrics "[Verse] <quick lyrics> [Chorus] <catchy hook>" \ --quality draft --duration 60
Present all 4 variants with paths and suggest: "Want me to refine any of these? I can repaint sections, change the style, or generate more in this direction."
Make full songs on your own computer by describing them in plain words. claude-music turns Claude Code into a music studio, powered by ACE-Step 1.5. Type "make me a chill lo-fi beat" and get a finished track in about 15 seconds.
Analyzes audio files for BPM, musical key, loudness (LUFS), duration, format, and quality metrics. Uses ffprobe for metadata and…
Songwriting guide for ACE-Step music generation. Helps craft captions (style descriptions), lyrics with structure tags, and…
Creates cover versions and style transfers of existing songs using ACE-Step 1.5. Takes a reference audio file and generates a new…
Post-processing for generated music. Default path is FFmpeg loudness normalization (fast, CPU-only). Escape hatches: AI vocal…
Exports music for specific platforms with optimal format, loudness, and metadata. Supports Spotify, Apple Music, YouTube, TikTok,…
Generates music from text descriptions and lyrics using ACE-Step 1.5's Python API. Creates full songs with vocals, instrumentals,…