agentleFS
Sign inStart free
eliftforlifeeliftforlife/claude-video-editing-skills/video-quality-check/SKILL.md

video-quality-check

Skill4 starsChanged 33 days agoMITView on GitHub

Check raw footage and a finished edit for the problems that make AI-edited videos look flat, soft or noisy and sound uneven - HDR footage, range mismatches, stacked compression, upscaling, loudness and true-peak. Use before editing new footage and before uploading a final video.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. demandsense-labs/linkedin-ads-skills★ 9same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run this on the raw takes before editing and on the final file before uploading.

    line 8
  2. Very specific:

    Audio: Check loudness (ebur128) and look for clipping in the raw file: a sample peak at 0 dBFS means the mic clipped and no edit can fully …

    line 20
  3. Distinctive:

    Keep intermediates near-lossless: x264 CRF ≤ 10, 10-bit.

    line 25
  4. Distinctive:

    Don't add animated grain. It eats bitrate and turns to blotches after YouTube's encode.

    line 27

≈ “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 quality check

Run this on the raw takes before editing and on the final file before uploading. Report what you find in plain words and what to change.

Raw footage

ffprobe -v error -select_streams v:0 -show_entries stream=width,height,r_frame_rate,pix_fmt,color_range,color_transfer,color_primaries -of compact <take>
  • HDR. color_transfer=arib-std-b67 (HLG) or smpte2084 (PQ) means HDR. Treated like normal video it comes out flat and grey. Best fix: tell the creator to turn off HDR Video (iPhone: Settings › Camera › Record Video). Otherwise tone-map to SDR BT.709 once, at the very first step.
  • Range. iPhone SDR is often full range (yuvj420p, color_range=pc). Convert to limited (tv) range once, explicitly, or blacks and whites get crushed or washed out.
  • Brightness. Measure the average luma (signalstats, YAVG). Under ~35/255 means a dim room. Fix the light, don't add darkening grades or vignettes on top.
  • Resolution. 1080p is enough for talking heads. Keep punch-ins modest (≤1.15×), since every zoom is an upscale.
  • Audio. Check loudness (ebur128) and look for clipping in the raw file: a sample peak at 0 dBFS means the mic clipped and no edit can fully fix it.

The edit pipeline

Count the lossy encodes from raw to upload. Every one costs detail, worst in dark shadows.

  • Keep intermediates near-lossless: x264 CRF ≤ 10, 10-bit.
  • Composite graphics in one final pass. Don't round-trip frames through JPEG.
  • Don't add animated grain. It eats bitrate and turns to blotches after YouTube's encode.

Final file

  • Video: H.264 High, yuv420p, BT.709 tags, CRF ~14, +faststart.
  • Loudness: about -14 LUFS integrated. True peak ≤ -1 dBTP: limit with oversampling (e.g. aresample=192000,alimiter,aresample=48000), since sample-peak limiting alone can still overshoot after AAC.
  • Music under speech: about 18–22 dB below the voice.
  • Re-transcribe the final voice track and read it top to bottom. It catches clipped first words, repeated phrases and stray syllables that you'll miss by ear.

Report each problem with the measured number, why it matters, and the one-line fix.

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