agentleFS
Sign inStart free
45ck45ck/video-evaluator/skills/video-technical-review/SKILL.md

video-technical-review

Skill2 starsChanged 7 months agoMITView on GitHub

Review a rendered video for technical defects such as resolution mismatch, missing or near-silent audio, black or white frames, edge gutters, low motion, sparse caption bands, and layout issue pass-through.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this after a video has been rendered and you need a deterministic technical audit before human or model review.

    line 8

≈ “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

Video Technical Review

Use this after a video has been rendered and you need a deterministic technical audit before human or model review.

This skill owns:

  • probing video resolution, duration, frame rate, and audio streams
  • sampling frames for black/white frames, bright edges, black gutters, caption band sparsity, and low-motion runs
  • measuring audio volume when an audio stream exists
  • preserving known issue codes from content-machine audit reports
  • writing video-technical.report.json, contact-sheet.png, and contact-sheet.metadata.json

Inputs

Required:

{
  "videoPath": "./output/example-run/output.mp4"
}

Optional fields:

  • outputDir: directory for report artifacts; defaults next to the video.
  • expectedWidth and expectedHeight: default to 1080 and 1920.
  • expectAudio: emit missing-audio when no audio stream exists, default true.
  • expectCaptions: check bottom caption band sparsity, default true.
  • frameSampleCount: number of frames to sample, default 12.
  • layoutReportPath: pass through issues whose codes begin with layout-.

Outputs

The result contains reportPath, report, contactSheetPath, contactSheetMetadataPath, and contactSheetMetadata. The report is written to video-technical.report.json.

Preserved issue codes:

  • wrong-resolution
  • missing-audio
  • near-silent-audio
  • white-flash-or-white-frame
  • black-frame
  • white-edge-artifact
  • black-gutter-artifact
  • low-motion-run
  • caption-band-sparse
  • layout-*

Interpretation Notes

The visual checks are sampled-frame heuristics. Treat them as triage evidence: they catch obvious render failures and artifact classes, but they do not replace watching the source video when a borderline issue matters.

Repo-side runner:

node --import tsx scripts/harness/video-technical-review.ts

Installed-pack runner:

node ./.video-evaluator/agent/run-tool.mjs video-technical-review

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