AudioCraft Audio Generation
Orchestra-Research/AI-Research-SKILLs
Generates music from text descriptions with MusicGen and sound effects with AudioGen, using Meta's AudioCraft PyTorch library with melody and style conditioning.
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
$ npx skills add autonomous-ai/openharness --skill score -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness score --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/score/skills/score .claude/skills/score && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "score" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/score into .claude/skills/score/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "score", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/scoreType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autonomous-ai/openharness --skill score -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness score --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/score/skills/score .agents/skills/score && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "score" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/score into .agents/skills/score/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "score", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill score -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness score --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/score/skills/score .cursor/skills/score && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "score" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/score into .cursor/skills/score/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "score", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/score/skills/score--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autonomous-ai/openharness --skill score -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness score --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/score/skills/score .gemini/skills/score && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "score" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/score into .gemini/skills/score/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "score", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autonomous-ai/openharness scoreInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autonomous-ai/openharness --skill score -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/score/skills/score .github/skills/score && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "score" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/score into .github/skills/score/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "score", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill score -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness score --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/score/skills/score .opencode/skills/score && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "score" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/score/skills/score into .opencode/skills/score/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "score", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
scoreTurns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
The skill works inside the Score harness on trusted LilyPond projects. The agent first records the brief, assumptions, timing, instrument transpositions and difficulty limits in `ensemble.json`, then writes reusable concert-pitch variables in `score.ly`. The builder adds key, meter, tempo, the printed score, parts and MIDI proofs, so the source is never transposed a second time for a transposing instrument.
The agent runs `render-score.sh`, then inspects `.harness/score.json` and every printed PDF page, treating LilyPond warnings as errors to fix in the music or layout. A failed requirement is read from `.harness/failed-score.json`, and earlier versions are kept under `.harness/history/`. You listen in a `score.html` viewer with play and pause, seeking, player mute and solo, slowdown, bar loops and part selection, and the browser can save a WAV of up to 3 minutes. The delivery is `score-project.zip` with the full PDF and MIDI, individual parts and slower solo and minus-one MIDI.
Read from SKILL.md and the folder at commit 50da5db. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 9 files in scripts/ (JavaScript and Shell), which the agent can run.
Shell commands in SKILL.md call:
shFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Score Music Composer loads about 1.1k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 52 tokens; SKILL.md has 582 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from autonomous-ai/openharness at commit 50da5db, republished under its MIT licence (© autonomous-ai). 582 words, ~1,115 tokens.
.claude/skills/score/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.The user does not need instruments or notation vocabulary. If they want to listen, start with mood, purpose, duration and a useful instrumentation; state assumptions and offer an audible first version. If they have real players, capture each player's instrument, written range and experience. Do not turn the starter trio or any particular difficulty limit into a universal requirement.
Read the ensemble contract before changing player setup, timing, difficulty or source exports.
Save the actual brief, assumptions, timing, instrument transpositions and
difficulty limits in ensemble.json. These are requirements, not values to
infer from whatever the generated notes happen to contain.
Compose reusable concert-pitch variables in score.ly; the builder adds
the initial key, meter, tempo, printed score, parts and MIDI proofs. Do not
transpose the source again for a B-flat part or override staff transposition.
Give the music a deliberate shape: phrases, breathing space, contrast, accompaniment and an ending appropriate to the request. A successful compiler does not supply those decisions.
Run:
sh "$SCORE_SKILLS/score/scripts/render-score.sh"Inspect .harness/score.json and every printed PDF page, including individual
parts. Check collisions, readability, instrument labels and sensible breaks.
LilyPond warnings are errors. Correct the music or layout, not the warning policy.
On a failed requirement, read .harness/failed-score.json. Fix the music while
retaining the user's limits. Change a requirement only when the request
genuinely changes; explain a conflict instead of quietly widening a range.
For a targeted revision, verify the requested change and compare unaffected
parts. Keep a useful previous version; generated handoffs are retained under
.harness/history/.
Use score.html in the actual viewer. Exercise play/pause, seeking into a held
note, player mute/solo, slowdown, bar loops and part selection. No instrument
is needed. The browser can save a WAV of the current mix/loop (up to 3 minutes).
Save/restore listening setup as JSON; no local storage is required.
The source-backed delivery is score-project.zip: full PDF/MIDI, individual
parts, slower solo/minus-one MIDI, the saved brief, allowlisted sources and
standalone rebuild tools. Test important downloads. Browser controls and WAV
exports do not change score.ly or the prebuilt practice MIDIs. To change the
composition, edit the sources and rebuild.
Report the version, checks and listening/visual review actually performed. Offer concrete revisions in the user's language (“make the ending warmer,” “remove the busy line”), not a requirement to learn notation first.
Setup installs LilyPond 2.26.0 when needed on supported Macs/Linux x86-64; the builder
finds that managed runtime automatically. Node 20+ comes from the runtime helper.
LILYPOND_BIN overrides the binary. Only compile trusted input: LilyPond can execute Scheme and read local
files. The source allowlist makes delivery explicit; it is not a Scheme sandbox.
Do not add unrelated files, credentials or recordings to the portable project.
Ready means fresh engraving and the saved mechanical requirements passed, not proof of musical quality, comfort, breath control, fingering, physical playability or permission to use an arrangement. A synthesized sketch is not a recording or sampled performance. No real-player testing is implied.
This checked workflow supports constant meter/tempo, complete bars and pitched staves. See the contract for limits and excluded cases. Original native MIDI is retained; practice exports and browser audio ignore pedal, bends and other expressive controllers. The browser uses simple oscillators, not a sound library.
Legacy score.ly projects containing full layout/MIDI blocks still engrave
without an ensemble contract, but remain unready for checked delivery. Preserve
their source and extract music variables deliberately when upgrading. Do not
blindly replace a user's composition with the template.
© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 10 other files (scripts, references) in store/agents/score/skills/score of autonomous-ai/openharness.
Open the folder on GitHubat commit 50da5db
Score Music Composer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Score Music Composer this skillautonomous-ai/openharness | 1.1k | — | ~1.1k | Automated safety check: Pass | MIT | |
| AudioCraft Audio GenerationOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.9k | Automated safety check: Pass | MIT | |
| HyperFrames Media Useheygen-com/hyperframes | 59k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Musictadaspetra/loop | 296 | 3 repos | ~827 | Automated safety check: Pass | MIT | |
| VRGDG H3 Short Film Pipelinevrgamegirl19/comfyui-vrgamedevgirl | 760 | — | ~4.2k | Automated safety check: Pass | Custom licence | |
| Mureka Music MakerSkyworkAI/Skywork-Skills | 203 | 1 repos | ~3k | Automated safety check: Pass | MIT |
Orchestra-Research/AI-Research-SKILLs
Generates music from text descriptions with MusicGen and sound effects with AudioGen, using Meta's AudioCraft PyTorch library with melody and style conditioning.
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
tadaspetra/loop
Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.
vrgamegirl19/comfyui-vrgamedevgirl
Builds an AI short film in a local ComfyUI with the VRGDG Video Builder, MiniMax H3 scenes, reference images, a music score, QA and a final edit.
SkyworkAI/Skywork-Skills
Generates songs, instrumentals and lyrics through the Mureka API, turning plain-language descriptions into structured music prompts first.
digitalsamba/claude-code-video-toolkit
Generates narration, sound effects and cloned voices through the ElevenLabs API, with model and setting choices tuned to the content's style.
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
autonomous-ai/openharness
Starts a local CAD Viewer server for a directory of CAD, robot-description or DXF files and returns a live review link, reusing a running instance when one already serves that directory.
Categories
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack. The skill works inside the Score harness on trusted LilyPond projects.ly`.
Score Music Composer fits situations like: composing a short piece for a specific ensemble with set difficulty limits; revising one part of an existing LilyPond score without disturbing the rest; making practice tracks for players who need a slower or minus-one version.
Run `npx skills add autonomous-ai/openharness --skill score -a claude-code`. Or copy the skill folder (store/agents/score/skills/score in autonomous-ai/openharness) into .claude/skills/score in your project. Claude Code loads it when a task matches its description.
Run `npx skills add autonomous-ai/openharness --skill score -a codex`. Or copy the skill folder (store/agents/score/skills/score in autonomous-ai/openharness) into .agents/skills/score in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill score -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/score, .gemini/skills/score, .github/skills/score and .opencode/skills/score in your project.
Going by SKILL.md and its folder, Score Music Composer needs JavaScript and a shell for the scripts in its folder and the command-line tools its instructions call (sh). Our summary lists: The Score harness with LilyPond available; A browser to open the `score.html` viewer.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Score Music Composer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Score Music Composer: AudioCraft Audio Generation (Orchestra-Research/AI-Research-SKILLs, 13k stars), HyperFrames Media Use (heygen-com/hyperframes, 59k stars), Music (tadaspetra/loop, 296 stars) and VRGDG H3 Short Film Pipeline (vrgamegirl19/comfyui-vrgamedevgirl, 760 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,149 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 8, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.