music-generator
Skill5 starsChanged 3 months agoApache-2.0View on GitHub
Generate music using Google Lyria 3 (DeepMind). Use for "生成音乐", "作曲", "写一首曲子", "generate music", "create a song", "compose", "piano piece", "钢琴曲", "make a beat", "生成钢琴曲", "来一首歌".
- Reads credentials
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- choms0521/my-claude-skillstheir own version, first seen Apr 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- choms0521/my-claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository54 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-teamsSkill
- bilibili-channelSkill
- bot-configSkill
- browser-cliSkill
- bwrap-bypassSkill
- cc-pages-backupSkill
- chat-styleSkill
- chinese-dictationSkill
- code-wiki-reconSkill
- deck-builderSkill
- docx-form-fillerSkill
- evolutionSkill
- explainer-distillSkill
- feishu-bitableSkill
- feishu-docSkill
- feishu-mailSkill
- feishu-sheetSkill
- feishu-user-msgSkill
- fireworks-tech-graphSkill
- frontend-slidesSkill
- gemini-ui-reviewerSkill
- hk-busSkill
- hk-share-award-tax-dipn38Skill
- imagen-generatorSkill
- issue-handlerSkill
- lecture-videoSkill
- lecture-voiceSkill
- lesson-read-aloudSkill
- live-canvasSkill
- lustre-mounterSkill
- manim-teaching-figuresSkill
- math-video-tutorSkill
- memory-gcSkill
- memory-lintSkill
- multimodal-explainerSkill
- notifySkill
- page-styleSkill
- paper-explainerSkill
- session-handoffSkill
- skill-creatorSkill
- smoke-testSkill
- study-materialSkill
- tmux-installerSkill
- tmux-orchestratorSkill
- tpuguruSkill
- tts-generatorSkill
- veo-generatorSkill
- vscode-referenceSkill
- weather-forecastSkill
- wechat-readerSkill
- wikiSkill
- youtube-channelSkill
- zsh-installerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 64
NO copyrighted references: Never name specific compositions, artists, or songs — the API will block with PROHIBITED_CONTENT.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Music Generator (Google Lyria 3)
Generate music using Google Lyria 3 Pro / Clip (DeepMind) via Gemini API, save to CC Pages, and share.
Two models:
- Lyria 3 Clip (
lyria-3-clip-preview) — 30-second clips, fast iteration - Lyria 3 Pro (
lyria-3-pro-preview) — full-length songs (1-3 minutes)
Usage
~/.claude/skills/music-generator/scripts/music-generate.sh "your music prompt"Options
# Quick 30s clip (default)
~/.claude/skills/music-generator/scripts/music-generate.sh "a dramatic solo piano piece in C minor"
# Full-length song (1-3 min)
~/.claude/skills/music-generator/scripts/music-generate.sh "epic orchestral film score" --duration full
# Specify style, key, tempo
~/.claude/skills/music-generator/scripts/music-generate.sh "jazz trio" --style jazz --key "Bb major" --tempo 140
# Allow vocals (default: instrumental only)
~/.claude/skills/music-generator/scripts/music-generate.sh "pop ballad with singing" --vocal
# Custom output filename
~/.claude/skills/music-generator/scripts/music-generate.sh "ambient soundscape" --output my-ambient
# Combine options
~/.claude/skills/music-generator/scripts/music-generate.sh \
"virtuoso solo piano, Late Romantic style, dramatic arpeggios and singing melody" \
--duration full --key "C# minor" --tempo 72 --output concert-pieceOutput
- Audio saved to
$CC_PAGES_WEB_ROOT/assets/music/as MP3 - Returns the public URL:
$CC_PAGES_URL_PREFIX/assets/music/{filename}.mp3
Workflow
# 1. Generate music
URL=$(~/.claude/skills/music-generator/scripts/music-generate.sh "solo piano nocturne" --duration full)
# 2. Share URL or embed in HTML
echo "Listen: $URL"Prompt Engineering Tips
- Use timestamps for structure:
[0:00-0:25] slow intro, [0:25-1:00] build intensity, [1:00-1:30] climax - Use Italian musical terms: Allegro, Pianissimo, Rubato, Con fuoco, Crescendo, Sforzando
- Specify instrumentation explicitly: "solo piano", "string quartet", "jazz trio with piano, upright bass, and brushed drums"
- NO copyrighted references: Never name specific compositions, artists, or songs — the API will block with PROHIBITED_CONTENT. Use generic style descriptions instead ("Late Romantic virtuoso piano", "bebop jazz")
- Repeat "NO vocals" for instrumental: Say "Instrumental only. NO vocals. NO singing." at least twice if you want pure instrumental
- Describe dynamics and emotion: "haunting and melancholic opening, building to a passionate fortissimo climax, then resolving with gentle pianissimo"
Models
| Model | Duration | Best For |
lyria-3-clip-preview (default) | ~30s | Quick previews, iteration, short loops |
lyria-3-pro-preview | 1-3 min | Full compositions, concert pieces |
Prerequisites
google-genaiPython SDK (pip install google-genai)GEMINI_API_KEYenvironment variable set- CC Pages (
$CC_PAGES_WEB_ROOTand$CC_PAGES_URL_PREFIX)
Files
~/.claude/skills/music-generator/scripts/
├── music-generate.sh # Entry point (exec wrapper)
└── music-generate.py # Core logic (google-genai SDK)
$CC_PAGES_WEB_ROOT/assets/music/ # Generated audio (web-accessible)Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

