review-ugc-render

Mandatory 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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable gating skill with a clear validated workflow and a strong failure-recovery table. Main weaknesses are mild description/body redundancy and two in-body references to files (tests, stitch_replacement.py) that are not present in the bundle.

Suggestions

Ship or remove the referenced tests/test_review_render.py and stitch_replacement.py, or relabel them as out-of-bundle (e.g. "in the content-goose repo") so the in-body paths are not dangling.

Trim the opening blockquote and the "Why this exists" example, which restate the description's human-vetted→human witted case; one canonical mention is enough.

Consider adding common-synonym trigger terms (e.g. "caption accuracy", "spoken-word QA") to broaden natural recall beyond internal recipe/atom names.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes competence; the mis-voicing examples and Seedance behavior are earned, Claude-unknown context. The intro blockquote and "Why this exists" partly restate the description's example, which could be trimmed.	4 / 5
Actionability	Gives a copy-paste invocation with all flags, explicit exit-code semantics (0/2/3), a report-line→root-cause→fix table, and a documented Inputs section — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Clear sequence (persist approved script → render → run gate → exit code decides publish) with explicit validation checkpoints and a feedback loop ("Re-run after every fix / re-roll until it PASSES") plus a failure-recovery table.	5 / 5
Progressive Disclosure	Well-organized sections with the single shipped script referenced by path and external content-goose pointers kept one level deep. However the body cites tests/test_review_render.py and stitch_replacement.py, neither of which ships in the bundle — minor dangling-reference gaps.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A precise, well-scoped description that covers what, when, and the specific defect class it catches, with concrete actions rather than abstractions. Trigger terms are domain-internal but accurate and distinctive.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Transcribes the finished render's AUDIO with Whisper", "word-diffs it against the approved spoken script", "gates set_final_render" — and enumerates the blocked defects (mis-voiced word, dropped phrase, silent render) for comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (transcribe → word-diff → gate) and when ("Every ugc-video-formats recipe runs this after render and BEFORE set_final_render") with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Good domain keywords (UGC video render, review gate, transcript, script, set_final_render, Whisper) that a user in this workflow would say, but coverage leans on internal recipe/atom jargon and omits common synonyms or file extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (audio-vs-script integrity gating for UGC renders) with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/ads/packs/ugc-video-formats/review-ugc-render/SKILL.md
Commit: 2523432

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.