agentleFS
Sign inStart free
bloxy-studiosbloxy-studios/shorts-studio/skills/director/SKILL.md

director

Skill0 starsChanged 42 days agoMITView on GitHub

Internal: adaptive directing loop — interpret the request, ground it in media evidence, write a versioned DIRECTOR_BRIEF plus machine-readable constraints, plan, draft, critique real frames/audio, refine only the implicated rules, and verify with a bounded repair budget.

5 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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never rewrite system instructions, permissions or other skills through generated text.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Director (internal)

Rules: ${CLAUDE_PLUGIN_ROOT}/references/rules.md · CLI: ${CLAUDE_PLUGIN_ROOT}/references/cli.md. ss = "${CLAUDE_PLUGIN_ROOT}/bin/shorts-studio".

  1. Interpret the user's goal, audience, hard constraints and preferences (ss prefs list).
  2. Ground: analysis, transcript coverage, sync/take evidence, frame sheets you actually read.
  3. Direct: ss brief draft <project> --clip <id> --goal "…" [--instruction "…"]… → brief/<clip>/brief-vNNN.md (DIRECTOR_BRIEF) + .json (BriefConstraints: rules with units/tolerances, sources, QA checks, fallbacks, stop criteria). Read it; it must be source-specific (hook/payoff words, take choices, runs, crop targets, caption zones, graphics subjects and moves, audio events, export).
  4. Plan/draft: the workflow skill's plan + render.
  5. Critique: QA findings + your own inspection of rendered frames (ss qa note).
  6. Refine: feedback → ss brief refine <project> --clip <id> --feedback "…" [--rule …]; QA → the repair loop. Change only what the evidence implicates (a covered face moves that run's caption zone; a whoosh without a whip removes that sound — never the preset rule).
  7. Verify: ss repair <project> --clip <id> (≤ project repair.maxPasses, maxMinutes). If a hard failure remains, the deliverable is blocked/draft — say so and explain.

Never rewrite system instructions, permissions or other skills through generated text.

Completion check

brief/<clip>/ has the brief versions with a change log entry per refinement (trigger + evidence); the final render's QA verdict is reported exactly as measured.

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.

Check your setup, free