agentleFS
badgidsbadgids/Story-Film-Skills/skills/media-qc/SKILL.md

media-qc

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Review generated candidate takes with structured script-faithfulness, identity, background, spatial, action, motion, physics, artifact, dialogue-sync, and subtitle-sync checks before creative take selection.

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

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read core contract, MEDIA_QC.md, source shot brief, take record, approved references, and adjacent approved material when continuity …

    line 13
  2. Distinctive:

    Use pass, warn, fail, not-applicable, or not-checked for each relevant dimension and provide concise evidence.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Media QC

Workflow

  1. Read core contract, MEDIA_QC.md, source shot brief, take record, approved references, and adjacent approved material when continuity matters.
  2. Inspect the actual generated media. Do not score from the prompt alone.
  3. Append or update the take's record in 04_generation/take_qc.jsonl.
  4. Use pass, warn, fail, not-applicable, or not-checked for each relevant dimension and provide concise evidence.
  5. Optional automated metrics may be recorded with evaluator/version metadata, but do not convert them into taste judgments automatically.
  6. Set overall to fail for hard script, identity, continuity, physics, corruption, or sync failures that make the take unusable as planned. For visible dialogue with approved-audio authority, treat wrong speaker ownership, unexpected mouth movement on a non-speaker, or generation/review audio hash drift as a hard sync failure.
  7. Pass the QC record to take-selection.

Done

The take has an evidence-backed production-quality record that separates objective/observable defects from later creative preference.

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.