review-ugc-render
FeaturedMandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.
Install
Quality Score: 97/100
Skill Content
Details
- Author
- gooseworks-ai
- Repository
- gooseworks-ai/goose-skills
- Created
- 6 months ago
- Last Updated
- 1 weeks ago
- Language
- Python
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
review-gate
Independently review one generated content item before it is published, for an agent built with content-agent-kit. Use during a daily run before publishing each item, or when the user asks to "review this item / check before posting". Returns a pass/fail verdict with specific issues.
ugc-fixloop
the UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt before render (vet_seedance_prompt.py, routed through the openai-proxy). Fetch it into a one-shot UGC recipe so both scripts resolve on any machine and the vet call bills the Ads agent.
review-gate
Use when closing work — when claiming done / complete / ready / shipping / about to push or open a PR — or when reviewing quality of a change before merge. Runs the tiered review gate (L1 code review, smoke test, proof the change is tested, adversarial review with cross-layer contract check, a recovery plan for Tier 3) and refuses to mark complete until the tier's required evidence is in `.claude/reviews/<branch>.md`.