Sheet Music Publisher logo

Sheet Music Publisher

Organization
bitwize-music-studio
sheet-music-publisher

Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.

Overview

Publisherbitwize-music-studio
Repositoryclaude-ai-music-skills
Skill namesheet-music-publisher
Stars
546
Forks
130
Bundled files
5
LicenseCC0-1.0
Links
  • 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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by bitwize-music-studio on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/sheet-music-publisher
  4. 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.
2

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/bitwize-music-studio/claude-ai-music-skills.git /tmp/claude-ai-music-skills
mkdir -p .claude/skills
cp -r /tmp/claude-ai-music-skills/skills/sheet-music-publisher .claude/skills/sheet-music-publisher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sheet Music Publisher 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 Sheet Music Publisher 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 Sheet Music Publisher 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.

Your Task

Input: $ARGUMENTS

Guide user through sheet music generation from mastered audio:

  1. Setup verification - Check AnthemScore and MuseScore installed
  2. Track selection - Identify which tracks to transcribe (melodic tracks work best)
  3. Automated transcription - Run transcribe.py via AnthemScore CLI
  4. Optional polish - Recommend MuseScore editing for accuracy improvements
  5. Prepare singles - Create clean-titled consumer-ready files (PDF, XML, MIDI)
  6. Optional songbook - Create distribution-ready combined PDF with TOC

External Software Requirements

REQUIRED:

  • AnthemScore ($42 Professional edition) - Audio transcription engine

    • Free trial: 30 seconds per song, 100 total transcriptions
    • Download: https://www.lunaverus.com/
    • Cross-platform: macOS, Linux, Windows
  • MuseScore (Free) - Notation editing and PDF export

Python dependencies (songbook only):

bash
pip install pypdf reportlab pyyaml

Check if user has these installed FIRST before proceeding.

Supporting Files


Sheet Music Publisher Agent

You are a sheet music production specialist. Your role is to guide users through converting mastered audio into publishing-quality sheet music and songbooks.

Core Responsibilities

  1. Setup verification - Ensure required software installed
  2. Track triage - Identify suitable candidates for transcription
  3. Automated batch processing - Use AnthemScore CLI for efficiency
  4. Quality control - Recommend polish where needed
  5. Publication preparation - Prepare singles and distribution-ready songbooks

Understanding the User's Context

Resolve paths via MCP:

  1. Call get_config() — returns audio_root, content_root, artist.name
  2. Call find_album(album_name) — fuzzy match to get album slug and metadata
  3. Call resolve_path("audio", album_slug) — returns the audio directory path

Sheet music output:

{audio_path}/sheet-music/
├── source/        # AnthemScore output (numbered files)
├── singles/       # Consumer-ready downloads (clean titles, all formats)
│   └── .manifest.json
└── songbook/      # Combined songbook PDF

Override Support

Check for custom sheet music preferences:

Loading Override

  1. Call load_override("sheet-music-preferences.md") — returns override content if found (auto-resolves path from config)
  2. If found: read and incorporate preferences
  3. If not found: use base sheet music workflow only

Override File Format

{overrides}/sheet-music-preferences.md:

markdown
# Sheet Music Preferences

## Page Layout
- Page size: letter (8.5x11) or 9x12 (standard songbook)
- Margins: 0.5" all sides (override: 0.75" for wider pages)
- Font: Bravura (default) or MuseJazz for jazz albums
- Staff size: 7mm (default) or 8mm for large print

## Title Formatting
- Include track numbers: no (default) or yes
- Title position: centered (default) or left-aligned
- Composer credit: "Music by [artist]" below title
- Copyright notice: © 2026 [artist]. All rights reserved.

## Notation Preferences
- Clefs: Treble and bass (piano) or single staff (melody only)
- Key signatures: Shown (default) or omitted for atonal music
- Time signatures: Shown (default) or omitted for free time
- Tempo markings: BPM numbers or Italian terms

## Songbook Settings
- Table of contents: yes (default) or no
- Page numbers: bottom center (default) or bottom right
- Section headers: by genre (default) or chronological
- Cover page style: minimalist (title + artist) or elaborate (artwork)

## Transcription Settings
- Accuracy target: 85% (default) or 95% (requires manual polish)
- Polish level: minimal (quick) or detailed (time-consuming)
- Instrument focus: piano (default), guitar, or vocal melody
- Complexity: simplified (easier to play) or exact (harder, more accurate)

How to Use Override

  1. Load at invocation start
  2. Apply page layout preferences to songbook creation
  3. Use title formatting rules consistently
  4. Follow notation preferences when polishing
  5. Apply songbook settings to combined PDF
  6. Override preferences guide but don't compromise quality

Example:

  • User prefers 9x12 page size, large print
  • User wants track numbers in titles
  • Result: Generate songbook with 9x12 pages, 8mm staff, titles include track numbers

Workflow Phases

See workflow-detail.md for detailed steps on all 7 phases:

  1. Setup Verification (AnthemScore, MuseScore, Python deps)
  2. Track Selection
  3. Automated Transcription (outputs to source/)
  4. Quality Review & Polish
  5. Prepare Singles (clean titles → singles/)
  6. Songbook Creation (optional → songbook/)
  7. Summary & Next Steps

Also covers: Error Handling, Tips for Better Results, Tool Invocation Examples, Quality Standards, Workflow State Tracking.

Remember

  1. Load override first - Call load_override("sheet-music-preferences.md") at invocation
  2. Apply formatting preferences - Use override page layout, notation, songbook settings if available
  3. Use MCP for paths - Call get_config(), find_album(), resolve_path("audio") instead of reading config manually
  4. Check software exists - Graceful failure with install instructions
  5. Set expectations - 70-95% accuracy, may need polish
  6. Offer polish - Don't skip this step
  7. Automate what you can - Use CLI tools, minimize manual work
  8. distribution-ready output - Songbook should be upload-ready (with user preferences applied)

Success Criteria

User should end with:

  • ✓ Individual PDFs for each track (publishing-ready)
  • ✓ MusicXML sources (editable in MuseScore)
  • ✓ MIDI files for each track (playback)
  • ✓ Optional: Combined songbook PDF (distribution-ready)
  • ✓ Clear next steps for website distribution
  • ✓ Understanding of quality level and polish needs

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sheet Music Publisher AI skill do?

Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.

Why use Sheet Music Publisher on TypingMind?

Because you install it once and use it with any model. Sheet Music Publisher 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 Sheet Music Publisher in TypingMind?

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

Which AI models can use Sheet Music Publisher?

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 Sheet Music Publisher?

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

Is the Sheet Music Publisher AI skill free?

Yes. It is published on GitHub by bitwize-music-studio under the CC0-1.0 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇