← ClaudeAtlas

generated-video-qualitylisted

Check AI-generated footage for the failure modes generation causes rather than deterministic editing -- identity drift, generation artifacts, motion that breaks physics, temporal discontinuity at stitch points, lip-sync drift, and prompt adherence. Use alongside video-quality for any candidate assembled from fal-ai or google-ai clips; never in place of it.
manishiitg/coding-agent-loop · ★ 13 · AI & Automation · score 63
Install: claude install-skill manishiitg/coding-agent-loop
# Quality checks specific to generated footage Use this only for the final assembled delivery MP4, alongside `video-quality`; do not run it after each generated preview clip. `video-quality` covers what applies to every video this product makes: decode/duration/dimensions, black frames and freezes, legible text, a coherent edit, and a passing `quality-report.json`. Run it first and in full -- this skill does not repeat it. What this skill adds is the failure modes a camera cannot produce, because they only exist in generated footage: a face that drifts across shots, a sixth finger, a background that reflows between frames, motion that snaps rather than continues across a cut. A technical pass and a coherent-edit pass both miss these, because nothing about them fails to decode, and nothing about them is a black frame. Add these checks to the **same** `quality-report.json` `checks` map `video-quality` writes, alongside `technical`/`visual`/`audio`/`content`/ `captions`/`promise` -- one report, one file, not a second document to reconcile: ```json "checks": { "character_consistency": {"status": "pass", "evidence": ["officer.png vs shots 3,7,12: consistent"]}, "generation_artifacts": {"status": "pass", "evidence": ["no extra limbs, warped hands, or gibberish text observed"]}, "temporal_coherence": {"status": "pass", "evidence": ["motion continues across every stitch point checked"]}, "motion_plausibility": {"status": "not_applicable", "evidence": ["no complex physics