agentleFS
badgidsbadgids/Story-Film-Skills/skills/audio-master/SKILL.md

audio-master

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Build and render a synchronized full-program audio master from approved dialogue, voiceover, ambience, Foley, SFX, score, and music using an explicit project-relative mix manifest.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ../../references/AUDIO_MASTERING.md, the edit plan, voice/music/SFX cues, media registry, and approvals.

    line 13
  2. Very specific:

    Write or update 05_post/audio_mix.json with exact timeline starts, source trims, durations, gain, pan, and fades.

    line 14
  3. Very specific:

    Use scripts/audio_master.py PROJECT --manifest 05_post/audio_mix.json for the actual master.

    line 16
  4. Distinctive:

    Verify the output exists and preserve the renderer report.

    line 17
  5. Very specific:

    Run asset-approval to register the rendered master.

    line 18
  6. Very specific:

    Run delivery-qc when the master has delivery constraints.

    line 19
  7. Distinctive:

    Do not estimate a rendered waveform path.

    line 23

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Audio Master

Workflow

  1. Read ../../references/AUDIO_MASTERING.md, the edit plan, voice/music/SFX cues, media registry, and approvals.
  2. Write or update 05_post/audio_mix.json with exact timeline starts, source trims, durations, gain, pan, and fades.
  3. Reject unresolved or missing required media before final rendering.
  4. Use scripts/audio_master.py PROJECT --manifest 05_post/audio_mix.json for the actual master.
  5. Verify the output exists and preserve the renderer report.
  6. Run asset-approval to register the rendered master.
  7. Run delivery-qc when the master has delivery constraints.

Weak-model rule

Do not estimate a rendered waveform path. Do not treat cue descriptions as audio. Do not stretch exact dialogue merely to fill a picture gap.

Done

The project has a reproducible mix manifest and, when rendering was requested and FFmpeg succeeded, an actual synchronized audio master file.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.