agentleFS
badgidsbadgids/Story-Film-Skills/skills/crew-review/SKILL.md

crew-review

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Run bounded creative review using Critique-Correct-Verify or Debate-Judge for consequential story, screenplay, directing, storyboard, or shot decisions, with explicit criteria, persistent verdicts, and escalation instead of endless loops.

3 other projects use 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 and COLLABORATION_PROTOCOLS.md.

    line 13
  2. Distinctive:

    If one model performs multiple roles, isolate the passes and do not claim independent model consensus.

    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

Crew Review

Workflow

  1. Read core contract and COLLABORATION_PROTOCOLS.md.
  2. Define one review scope and the criteria before creating any alternate or critique.
  3. Choose Critique-Correct-Verify for fixable quality failures. Choose Debate-Judge for a real choice between materially different approaches.
  4. If one model performs multiple roles, isolate the passes and do not claim independent model consensus.
  5. Save durable review rounds under 00_project/reviews/<scope-id>/ when the decision affects downstream work.
  6. Obey the protocol iteration cap. After repeated failure or an authority conflict, record ESCALATE and state the exact decision needed.
  7. Apply accepted corrections through the owning specialist skill. A reviewer does not silently edit an approved upstream artifact.

Done

The scope has a PASS or an explicit escalated decision, the criteria and unresolved items are recorded, and the review did not exceed its bounded iteration count.

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.