director-pass
Skill2 starsChanged 5 months agoNo licenceView on GitHub
An agentic, vision-driven final QA/repair pass — a Claude "director" WATCHES the finished short (a contact sheet of frames sampled across the whole clip + the transcript + the sidecar plans) and decides, in natural language, what is broken ANYWHERE (cold open, dead/rambling tail, a tonally-wrong b-roll match, a wrong-person punch-in, mistimed captions, a too-hot music bed, a flat hook) — not just the cold open, not just a fixed route vocabulary. It then APPLIES the fixes it can from a bounded, pixel-safe set (tail_trim via cut-clip; music_down via a bg-music re-mix) and SURFACES everything else as an honest edit list, re-reviewing up to DIRECTOR_MAX_ITERS times. Layered ON TOP of grade-clip (the cheap proxy floor) + fix-cold-open (the closed-vocab cold-open repair). NON-FATAL, idempotent (.dpmeta). Two modes — preventive in-chain (the pre-mix .ctaed.mp4 + clip_NN.* sidecars are co-located, so music_down can re-mix) and curative standalone/backlog (a finished output clip → tail_trim only, everything else surfaced — never fabricate a baked-in repair).
In this repository52 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analytics-feedbackSkill
- bg-musicSkill
- bookend-trimSkill
- brand-overlaysSkill
- broll-cleanupSkill
- broll-compositeSkill
- broll-pickSkill
- burn-subtitlesSkill
- chunk-captionsSkill
- cut-clipSkill
- cut-fillerSkill
- derive-thesisSkill
- end-cardSkill
- fill-verticalSkill
- first-span-feedbackSkill
- fix-cold-openSkill
- generate-titleSkill
- grade-clipSkill
- ingestSkill
- jump-cutSkill
- like-subscribe-overlaySkill
- loudnormSkill
- name-shortSkill
- pick-moodSkill
- pick-segmentsSkill
- profile-clipSkill
- qc-clipSkill
- reap-sourceSkill
- save-localSkill
- schedule-dripSkill
- scout-sourcesSkill
- segment-topicsSkill
- selection-reportSkill
- sfx-beatsSkill
- source-creditSkill
- sources-ledgerSkill
- speed-upSkill
- style-corpusSkill
- style-gateSkill
- switch-facesSkill
- tighten-paceSkill
- title-transitionSkill
- transcribeSkill
- trim-fillerSkill
- verify-bookendsSkill
- verify-coherenceSkill
- verify-completenessSkill
- visual-cadenceSkill
- watermarkSkill
- zoom-punchSkill
The file
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
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.

