Agent skill

Music Generation

by 0xsline in 0xsline/OpenChatCut

Generates instrumentals, songs, soundtracks and covers through Mureka, MiniMax, Atlas Cloud or Sonilo using the `submit_music` tool.

AGPL-3.0Auto-check passedMedia & Creative

Install Music Generation

skills CLI
$ npx skills add 0xsline/OpenChatCut --skill music -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install 0xsline/OpenChatCut music --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/0xsline/OpenChatCut.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/agent/skills/music .claude/skills/music && rm -rf skills-src

Use ~/.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/

Facts

Skill name
music
GitHub stars
2.2k
Token cost
~1.1k tokens
SKILL.md length
286 words
Files
5 (incl. references)
Skills in repo
31
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generates instrumentals, songs, soundtracks and covers through Mureka, MiniMax, Atlas Cloud or Sonilo using the `submit_music` tool.

  • Works in 5 steps: Confirm provider, mode, and whether… → Read the provider reference and pass… → Submit once, then call track_progress({… → …
  • Adding a background music bed under narration in a video project
  • SKILL.md covers Providers and modes, Shared workflow, Examples and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill routes a music request to one of four providers through `submit_music`, which returns a job ID that the agent polls with `track_progress` until the results are saved in the media pool. Mureka covers instrumental, song, prompt-song, soundtrack and track modes and is the default for ordinary background music, MiniMax offers text-to-music and cover, Atlas Cloud does text-to-music only, and Sonilo composes music from a finished video cut.

Each provider has its own reference file, and the agent passes only that provider's parameters. It generates only on an explicit request, since asking for two or three variants can multiply provider charges. A MiniMax cover needs exactly one of a reference asset ID or a cover feature ID, and the latter also needs lyrics. Placement, trim, loops, fades and ducking stay timeline operations, done once the real durations are known.

When your agent uses it

  • Adding a background music bed under narration in a video project
  • Scoring a finished cut with music composed from the video itself
  • Generating a cover of an existing track with MiniMax

Example prompts

  • “Generate a warm lo-fi piano instrumental to sit under the narration.”
  • “Score the finished cut with Sonilo.”
  • “Make a song with vocals using Mureka, one variant only.”

Requirements

  • Access configured for Mureka, MiniMax, Atlas Cloud or Sonilo
  • An editor session that exposes `submit_music` and `track_progress`

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Confirm provider, mode, and whether multiple paid variants are wanted.
  2. Read the provider reference and pass only that provider's parameters.
  3. Submit once, then call track_progress({ target:"generation", action:"wait", jobIds:[jobId] }).
  4. Use every returned asset when count produced multiple results; do not assume only the legacy result field exists.
  5. Place/trim/duck on the timeline only after actual durations are known.

What it can do on your machine

Read from SKILL.md and the folder at commit 2e6f4a2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Music Generation loads about 1.1k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 286 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.1k

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.

Safety

Auto-check passed

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from 0xsline/OpenChatCut at commit 2e6f4a2, republished under its AGPL-3.0 licence (© 0xsline). 286 words, ~1,092 tokens.

Download SKILL.mdSave it as .claude/skills/music/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
music
description
Music generation via Mureka, MiniMax, Atlas Cloud, and Sonilo. Use for instrumentals, songs, soundtracks, track/stem generation, covers, or video-conditioned scoring of the finished cut through `submit_music`.
user-invocable
true

Music

submit_music returns a generation jobId; call track_progress until every result is saved in the media pool. Placement, trim, loop, fades, and ducking remain timeline operations.

Providers and modes

ProviderModesReference
murekainstrumental, song, prompt-song, soundtrack, trackreferences/mureka.md
minimaxt2m, coverreferences/minimax.md
atlast2mreferences/atlas.md
sonilov2mreferences/sonilo.md

Select the named/configured vendor. Default to Mureka instrumental for ordinary BGM. Use Mureka song/prompt-song when its vocal or reference controls are wanted; use Mureka soundtrack for an image/video-driven score and track mode for generating a stem/track from a song/audio source. Use MiniMax for its text-to-music and cover models. Use Atlas Cloud for schema-backed text-to-music through its asynchronous audio API. Use Sonilo v2m when the music should be composed from the finished cut itself (a project video asset) rather than a text description.

Shared workflow

  1. Confirm provider, mode, and whether multiple paid variants are wanted.
  2. Read the provider reference and pass only that provider's parameters.
  3. Submit once, then call track_progress({ target:"generation", action:"wait", jobIds:[jobId] }).
  4. Use every returned asset when count produced multiple results; do not assume only the legacy result field exists.
  5. Place/trim/duck on the timeline only after actual durations are known.

Examples

ts
// Mureka instrumental (default count is deliberately 1)
submit_music({ provider: "mureka", mode: "instrumental", prompt: "Warm lo-fi piano bed under narration", count: 1 });

// Mureka lyrics song
submit_music({
  provider: "mureka", mode: "song", prompt: "Bright modern pop", gender: "female", count: 2,
  lyrics: "[Verse]\nCity lights open the night\n[Chorus]\nWe build the future in real time",
});

// Mureka prompt song
submit_music({ provider: "mureka", mode: "prompt-song", prompt: "A hopeful road-trip anthem", styles: ["pop", "folk"] });

// Score a project video or image
submit_music({ provider: "mureka", mode: "soundtrack", sourceAssetId: "videoAssetId", prompt: "Tense restrained documentary score" });

// Generate a stem from a Mureka song id
submit_music({ provider: "mureka", mode: "track", songId: "song-id", trackType: "Drums", prompt: "Tight punchy acoustic drums" });

// MiniMax instrumental / vocals
submit_music({ provider: "minimax", mode: "t2m", prompt: "Upbeat electronic tech intro", isInstrumental: true });
submit_music({ provider: "minimax", mode: "t2m", prompt: "Rainy night pop", lyricsOptimizer: true });

// MiniMax cover from a project audio asset
submit_music({ provider: "minimax", mode: "cover", prompt: "Warm acoustic coffee-shop cover", referenceAssetId: "audioAssetId" });

// Atlas Cloud text-to-music
submit_music({ provider: "atlas", mode: "t2m", prompt: "Cinematic ambient score with restrained piano", isInstrumental: true });

// Sonilo video-to-music from the rendered cut (prompt optional)
submit_music({ provider: "sonilo", mode: "v2m", sourceAssetId: "renderedCutAssetId" });
submit_music({ provider: "sonilo", mode: "v2m", sourceAssetId: "renderedCutAssetId", prompt: "Warm indie folk, no drums" });

Rules

  • Only generate after an explicit request; count 2–3 can multiply provider charges, so never add variants silently.
  • Mureka stream:true enables the provider's streaming task phase, but OpenChatCut still waits for durable final files.
  • MiniMax cover requires a configured music-cover* model and exactly one of referenceAssetId or coverFeatureId; coverFeatureId also requires lyrics.
  • Atlas Cloud supports t2m only and does not accept MiniMax cover/optimizer or Mureka-specific controls.
  • Never mix MiniMax audio-setting fields into Mureka or Mureka IDs/modes into MiniMax.
  • Generated music does not guarantee exact beat/drop timing; cut and align after generation.

© 0xsline, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in src/agent/skills/music of 0xsline/OpenChatCut.

  • SKILL.md
  • references/atlas.md
  • references/minimax.md
  • references/mureka.md
  • references/sonilo.md

Open the folder on GitHubat commit 2e6f4a2

Compare with similar skills

Music Generation 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.

Music Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Music Generation this skill0xsline/OpenChatCut2.2k—~1.1kAutomated safety check: PassAGPL-3.0
VRGDG H3 Short Film Pipelinevrgamegirl19/comfyui-vrgamedevgirl765—~4.2kAutomated safety check: PassCustom licence
Media Productionleon-ai/leon18k—~999Automated safety check: PassMIT
KrillinAI CLI Operatorkrillinai/OpenCreator13k—~869Automated safety check: PassApache-2.0
Music to Videoheygen-com/hyperframes60k3 repos~4.7kAutomated safety check: NotesApache-2.0
HyperFrames Audioheygen-com/hyperframes60k1 repos~6.5kAutomated safety check: PassApache-2.0

Similar skills

  • VRGDG H3 Short Film Pipeline

    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.

    765 GitHub stars~4.2k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Media Production

    leon-ai/leon

    Generates images, audio and video through Leon's media tools, joins them with FFmpeg, checks the output and attaches playable files for the owner.

    18k GitHub stars~999 tokensUpdated today
    Media & CreativeAuto-check passed
  • KrillinAI CLI Operator

    krillinai/OpenCreator

    Routes agents to the right KrillinAI command for subtitles, dubbing, video rendering, covers and speech, and explains how to read its JSON and manifest output.

    13k GitHub stars~869 tokensUpdated today
    Media & CreativeAuto-check passed
  • Music to Video

    heygen-com/hyperframes

    Turns a music track into a beat-synced HyperFrames video such as a lyric video, slideshow or kinetic promo, with any supplied images or clips cut onto the beat grid.

    60k GitHub starsUsed in 3 repos~4.7k tokens
    Media & CreativeAuto-check: notes
  • HyperFrames Audio

    heygen-com/hyperframes

    Mixes audio already placed in a HyperFrames composition: fades, gain, ducking under a voiceover, effect chains, automation and shared submix buses.

    60k GitHub starsUsed in 1 repo~6.5k tokens
    Media & CreativeAuto-check passed
  • Qiaomu Cut

    joeseesun/qiaomu-cut-skill

    把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频:介绍…

    372 GitHub stars~6.8k tokensUpdated 13 days ago
    Media & CreativeAuto-check: notes

More from 0xsline/OpenChatCut

All 31 skills in this repo
  • OpenChatCut Video Editing

    0xsline/OpenChatCut

    Connects an MCP-capable agent to the local OpenChatCut video editor to inspect and edit projects through draft edit sessions, with manual approval by default.

    2.2k GitHub starsUsed in 1 repo~655 tokens
    Auto-check passed
  • Video Shader Generator

    0xsline/OpenChatCut

    Generates WebGL shaders for video effects, transitions, masks and color grades in the OpenChatCut editor, trying built-in catalog effects such as zoom before making anything new.

    2.2k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed
  • AI Image Generation

    0xsline/OpenChatCut

    Generates still images through the submit_image tool, choosing among Fal.ai, gpt-image-2, nano-banana, MiniMax image-01 and Grok Imagine by configured keys.

    2.2k GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed
  • Livestream to Clips

    0xsline/OpenChatCut

    Cuts a livestream recording into evidence-backed, platform-ready clips by combining transcript, visual, audio and genre-specific signals.

    2.2k GitHub stars~2.7k tokensUpdated 4 days ago
    Auto-check passed
  • AI Video Generation

    0xsline/OpenChatCut

    Submits AI video generation jobs to Fal.ai, Seedance, Kling, MiniMax Hailuo, xAI Grok Imagine or OFox for text-to-video, image-to-video, transitions and clip extension.

    2.2k GitHub stars~4.3k tokensUpdated 4 days ago
    Auto-check passed
  • Generates text-to-speech narration and custom sound effects for a video timeline, keeping existing voiceover in sync after visual retiming edits.

    2.2k GitHub stars~4.4k tokensUpdated 4 days ago
    Auto-check passed

Works with

Questions about Music Generation

What does Music Generation do?

Generates instrumentals, songs, soundtracks and covers through Mureka, MiniMax, Atlas Cloud or Sonilo using the `submit_music` tool. The skill routes a music request to one of four providers through `submit_music`, which returns a job ID that the agent polls with `track_progress` until the results are saved in the media pool. Mureka covers instrumental, song, prompt-song, soundtrack and track modes and is the default for ordinary background music, MiniMax offers text-to-music and cover, Atlas Cloud does text-to-music only, and Sonilo composes music from a finished video cut.

When should I use Music Generation?

Music Generation fits situations like: adding a background music bed under narration in a video project; scoring a finished cut with music composed from the video itself; generating a cover of an existing track with MiniMax.

How do I install Music Generation in Claude Code?

Run `npx skills add 0xsline/OpenChatCut --skill music -a claude-code`. Or copy the skill folder (src/agent/skills/music in 0xsline/OpenChatCut) into .claude/skills/music in your project. Claude Code loads it when a task matches its description.

How do I install Music Generation in Codex?

Run `npx skills add 0xsline/OpenChatCut --skill music -a codex`. Or copy the skill folder (src/agent/skills/music in 0xsline/OpenChatCut) into .agents/skills/music in your project. Codex loads it when a task matches its description.

Can I use Music Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add 0xsline/OpenChatCut --skill music -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/music, .gemini/skills/music, .github/skills/music and .opencode/skills/music in your project.

What does Music Generation need to run?

SKILL.md names no scripts, command-line tools or credentials: Music Generation is instructions for the agent only. Our summary lists: Access configured for Mureka, MiniMax, Atlas Cloud or Sonilo; An editor session that exposes `submit_music` and `track_progress`.

Does Music Generation access the network?

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.

Is Music Generation safe to install?

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. Review the folder before installing.

What licence does Music Generation use?

Music Generation is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Music Generation use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 2k tokens, read only when the agent opens those files.

What are the alternatives to Music Generation?

Skills that share tags, products or a category with Music Generation: VRGDG H3 Short Film Pipeline (vrgamegirl19/comfyui-vrgamedevgirl, 765 stars), Media Production (leon-ai/leon, 18k stars), KrillinAI CLI Operator (krillinai/OpenCreator, 13k stars) and Music to Video (heygen-com/hyperframes, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Music Generation?

0xsline (a GitHub user) maintains it in 0xsline/OpenChatCut, which has 2,235 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 7, 2026.

Source: 0xsline/OpenChatCut on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.