Claude Music Compose

Community

AgriciDaniel

claude-music-compose

Songwriting guide for ACE-Step music generation. Helps craft captions (style descriptions), lyrics with structure tags, and choose optimal BPM/key/duration/time signature.

Overview

Publisher	AgriciDaniel
Repository	`claude-music`
Skill name	`claude-music-compose`
Stars	89
Forks	28
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by AgriciDaniel on GitHub. Read the source before you install it.

Installation

Install the Claude Music Compose AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/AgriciDaniel/claude-music/tree/main/skills/claude-music-compose
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/AgriciDaniel/claude-music.git /tmp/claude-music
mkdir -p .claude/skills
cp -r /tmp/claude-music/skills/claude-music-compose .claude/skills/claude-music-compose

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Claude Music Compose in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Claude Music Compose on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Claude Music Compose is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

claude-music-compose — Songwriting Assistant

This is a READ-ONLY reference skill. Claude uses this knowledge to help craft optimal inputs for /music generate.

Execution

This sub-skill runs in a forked context (context: fork) and delegates the actual composition planning to the music-composer agent (skills/claude-music/agents/music-composer.md). The agent returns structured JSON ready to hand to music_engine.sh generate.

The reference material below is what the agent reads when it plans. It is also what you read when the user wants to learn the conventions rather than auto-compose.

Output Format

After composing, produce these for the generate command:

Caption (-c): Style/genre/instruments/emotion (max 512 chars)
Lyrics (-l): Structured lyrics with tags (max 4096 chars)
Parameters: --duration, --bpm, --key, --time-sig, --language

Caption Crafting

Formula: Genre + mood + instruments + vocal style + production quality

Dimensions

Dimension	Examples
Genre	pop, rock, jazz, electronic, hip-hop, R&B, folk, classical, lo-fi, synthwave
Mood	melancholic, uplifting, energetic, dreamy, dark, nostalgic, euphoric, intimate
Instruments	acoustic guitar, piano, synth pads, 808 drums, strings, brass, electric bass
Timbre	warm, bright, crisp, airy, punchy, lush, raw, polished
Era	80s synth-pop, 90s grunge, 2010s EDM, vintage soul, modern trap
Production	lo-fi, high-fidelity, live recording, studio-polished, bedroom pop
Vocals	female vocal, male vocal, breathy, powerful, falsetto, raspy, choir
Rhythm	slow tempo, mid-tempo, fast-paced, groovy, driving, laid-back

Principles

Specific beats vague — "sad piano ballad, female breathy vocal" > "a sad song"
Combine 3-5 dimensions — anchors the direction precisely
Don't put BPM/key in caption — use dedicated parameters instead
Avoid conflicting genres — "ambient metal" confuses the model
Repetition reinforces — repeat elements you want emphasized
Less detail = more creativity — let the model surprise you

Lyrics Structure

Tag	Purpose
`[Verse]` / `[Verse 1]`	Narrative sections
`[Chorus]`	Emotional climax, hook
`[Pre-Chorus]`	Build energy before chorus
`[Bridge]`	Transition or elevation
`[Intro]`	Opening atmosphere
`[Outro]`	Ending/conclusion
`[Drop]`	Electronic energy release
`[Breakdown]`	Reduced instrumentation
`[Instrumental]`	No vocals section
`[Guitar Solo]`	Specific instrument solo
`[Fade Out]`	Fade ending

Density Rules

~2-3 words per second of audio
30s track: 60-90 words
60s track: 120-180 words
120s track: 240-360 words
Keep lines 4-8 words for vocal clarity
Simple, singable phrasing works best

Tips

Match lyrics emotion to caption mood
Avoid tongue twisters and complex vocabulary
Use line breaks between phrases
Chorus should be the most memorable/catchy section
Bridge should contrast with verse/chorus

Parameter Selection

BPM by Genre

Genre	BPM Range	Sweet Spot
Ballad	60-80	70
Lo-fi	70-90	80
R&B	80-100	90
Pop	100-130	120
Rock	110-140	125
House	120-130	125
Hip-hop	80-115	95
EDM	128-150	140
DnB	160-180	174
Trap	130-170	140

Duration Guide

Song Type	Duration	Notes
Jingle/Short	15-30s	TikTok, ad music
Standard	60-120s	Most songs
Full song	180-300s	Complete arrangement
Extended	300-600s	Ambient, DJ sets

For detailed reference: load references/prompt-guide.md and references/music-theory.md

Frequently asked questions

What does the Claude Music Compose AI skill do?

Songwriting guide for ACE-Step music generation. Helps craft captions (style descriptions), lyrics with structure tags, and choose optimal BPM/key/duration/time signature.

Why use Claude Music Compose on TypingMind?

Because you install it once and use it with any model. Claude Music Compose is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Claude Music Compose in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgriciDaniel/claude-music/tree/main/skills/claude-music-compose. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Claude Music Compose?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Claude Music Compose?

As many as you like. As long as a model supports skills, you can use Claude Music Compose with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Claude Music Compose AI skill free?

Yes. It is published on GitHub by AgriciDaniel under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Karpathy Guidelines

multica-ai

OrganizationPopular

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

Create Agent

Create a custom agent (.agent.md) for a specific job.

Create Hook

Create a hook (.json) to enforce policy or automate agent lifecycle events.

Generate Run Commands

microsoft

OrganizationPopular

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

Claude Music Compose

Overview