agentleFS
prajwal-svmprajwal-svm/product-promo-harness/skills/promo-critic/SKILL.md

promo-critic

Skill1 starsChanged 45 days agoMITView on GitHub

Critique a rendered promo or explainer video from the product promo harness like a harsh motion director (`promo critique` evidence: contact sheets, seam strips, phone sheet, sync and loudness measurements), hold it to the user's hard quality rules, score it, and drive the fix-and-rerender loop up to `promo ship`. Use when reviewing, critiquing, scoring or QA-ing a rendered promo video, or when a promo-video run reaches its critic gate.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Read review.md. Fix the three worst problems, re-render only the affected shots (promo scenes --shot <id>), promo assemble, and start the …

    line 22
  2. Very specific:

    No blur, anywhere: No blur filter, depth of field or motion blur on anything, no blurred background, no blur-in entrance, no …

    line 32
  3. Very specific:

    App truth: Never invent UI, copy, numbers, citations or identifiers.

    line 40
  4. Distinctive:

    Fonts are vendored: No CDN or network at render.

    line 45
  5. Distinctive:

    No CSS outlines or focus rings.

    line 47
  6. Distinctive:

    Every score is 8 or more, every pack checklist item passes, every automatic check passes and no hard rule is broken.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

promo-critic

One round

  1. promo verify first (determinism: the same frame whatever the seek order). Then promo critique (or promo critique --video renders/draft/animatic.mp4 for a structure round on the animatic, whose tech check fails on the half-size, 30 fps draft by design). It writes critic/<n>/evidence/ (contact sheets on the beats or every 0.5 s, a strip at every seam and at the fastest action, a phone-size sheet, a master sheet, the spectrogram, loudness.json, sync.json, tech.json), critic/<n>/summary.json and critic/<n>/PROMPT.md. It exits 1 when an automatic check fails.
  2. Fix failed automatic checks first (tech, loudness, sync_sfx, sync_vo, vo_wer, claims, determinism, hf_lint); they are facts, not taste. Re-render, re-assemble, critique again.
  3. Dispatch a fresh subagent that has not seen the plan or the code, on the most capable model. Give it only: the path to critic/<n>/, the instruction to read PROMPT.md, open every image in evidence/ and check every frame against the hard rules below (paste them verbatim), and to write review.md and scores.json next to PROMPT.md. Do not summarise the video for it.
  4. Read review.md. Fix the three worst problems, re-render only the affected shots (promo scenes --shot <id>), promo assemble, and start the next round.

Hard rules (any frame that breaks one fails the round)

  • Readability. Key text is 22 px or more on screen at 1080p on its beat. The camera pushes in on the element the line is about and frames whole components; no word is cropped. The evidence sheets are scaled down (22 px is about 4 px on the 360 px-wide phone sheet), so before dispatching, add full-size frames of the doubtful beats to evidence/ (ffmpeg -ss <t> -i renders/master.mp4 -frames:v 1 critic/<n>/evidence/full-<t>.png), or measure with a readability script that reads every visible text node's rendered height.
  • No blur, anywhere. No blur filter, depth of field or motion blur on anything, no blurred background, no blur-in entrance, no backdrop-filter. Fail any blur you see. Competitor names are kept out of frame by the beat or the crop, never blurred.
  • No white inner shadow, glow, feathered edge mask, vignette or grey scrim on any frame.
  • Cursor. A pointer (hand) cursor over clickables. Each click lands on the real target (button, row or field, never a label or panel title). The cursor arrives 0.3-0.5 s before the click.
  • Zooms. Smooth and accurate, landing framed on the exact element; nothing important clipped (no half dialogs, no cut-off documents or panel names); the app window is big enough to hold the content whole.
  • App truth. Never invent UI, copy, numbers, citations or identifiers. Values on screen are computed from the app; a lookup shows only real metadata. Compare against assets/capture/ and the app itself.
  • No dead frames. Something new every 2-4 s; never a hold on a sparse or empty grid.
  • Mascot or characters, when used. Hero scale when they are the shot, natural motion, no anatomy glitches (extra limbs, lost line work, foot slide).
  • Fonts are vendored. No CDN or network at render; a substituted font is a failure.
  • Public copy went through the humanizer skill: no em dash, no "not X but Y", no hype words.
  • No CSS outlines or focus rings.

Pass bar

Every score is 8 or more, every pack checklist item passes, every automatic check passes and no hard rule is broken. At least 2 rounds, at most 5. After round 5, stop and report what still fails; never claim success you did not measure.

The ship gate

promo ship accepts only the latest round, and only when its summary.json has ok: true, its scores.json has pass: true, and the video it judged is this master: the round records the SHA-256 of what it judged, so an animatic round or a re-assembled master does not count. The last round is always on the final master. promo ship --force ships anyway and writes that it did into the run README; use it only when the user says so. A film silent by design passes loudness and sync_sfx as "n/a": its shot list plans no VO lines and no SFX placements, and its pack's music mode is none. Anything planned but not made fails and names the step to run.

Honesty

Audio is checked by measurement (LUFS, true peak, sounds found at their planned events, ASR on the mix), not by ear: say so. A critic that praises everything is not working; if round 1 scores all 9s, ask the subagent to look again at the seam strips and the phone sheet.

Companion skills for the fixes: hyperframes-agent-render-gotchas (frames that differ by seek order, fonts, frozen renders) and ffmpeg-filtergraph-mix-master-gotchas (loudness, true peak, ducking, the master chain).

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.