agentleFS
badgidsbadgids/Story-Film-Skills/skills/asset-approval/SKILL.md

asset-approval

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Register and approve generated or imported media across reference, voice, dialogue, music, SFX, video, master, trailer, social, artwork, and release groups with one durable primary/alternate/reject state model.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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/MEDIA_REGISTRY.md, project dependencies, and the relevant source artifact.

    line 13
  2. Distinctive:

    Use one approval group per decision scope.

    line 16
  3. Distinctive:

    Keep useful alternates. Keep rejected and superseded history.

    line 18
  4. Very specific:

    Never select a QC-failed candidate without explicit qc_override: true and a concrete user-approved reason.

    line 19
  5. Very specific:

    Use scripts/media_registry.py for deterministic state changes when available.

    line 20
  6. Very specific:

    If a primary replacement affects downstream timing, identity, content, or continuity, run project-impact.

    line 21
  7. Very specific:

    Never infer approval from filename order, newest timestamp, highest seed, or generation success.

    line 25
  8. Distinctive:

    Every reviewed media group has zero or one primary, explicit alternates, preserved rejected history, and project-relative paths.

    line 29

≈ “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

Asset Approval

Workflow

  1. Read ../../references/MEDIA_REGISTRY.md, project dependencies, and the relevant source artifact.
  2. Register each concrete media candidate in 00_project/media_registry.jsonl with a new MEDIA-### ID.
  3. Preserve the domain source ID such as TAKE-###, VOICE-###, MUS-###, SFX-###, REF-###, TRL-###, or SOC-###.
  4. Use one approval group per decision scope.
  5. Inspect media and relevant QC before selecting a primary.
  6. Keep useful alternates. Keep rejected and superseded history. Rejection changes state; it does not physically delete a file.
  7. Never select a QC-failed candidate without explicit qc_override: true and a concrete user-approved reason.
  8. Use scripts/media_registry.py for deterministic state changes when available. Use scripts/media_lifecycle.py only after an explicit deletion or runtime-copy-repair request; it may delete only an exact eligible registered path and records the cleanup operation.
  9. If a primary replacement affects downstream timing, identity, content, or continuity, run project-impact.

Weak-model rule

Never infer approval from filename order, newest timestamp, highest seed, or generation success. Only media_approvals.json determines the current primary.

Done

Every reviewed media group has zero or one primary, explicit alternates, preserved rejected history, and project-relative paths.

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.