CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

An exemplary focused skill body: concise, fully actionable, with an explicit publish-gating workflow and a verification feedback loop. Progressive disclosure is appropriate for a single-file skill with one real bundled script.

DimensionReasoningScore

Conciseness

Lean prose that assumes competence — it names Whisper/ffmpeg as backends without explaining them, uses tight concrete examples (the vetted→witted mis-voice), and every section earns its place with no concept padding.

3 / 3

Actionability

Provides a fully executable copy-paste command with real script path and args, plus an exit-code table and a report-line→root-cause→fix table that is immediately actionable.

3 / 3

Workflow Clarity

Clear sequence with explicit checkpoints: persist approved-script.txt before render, run the gate after render, branch on exit 0/2/3, and "Re-run after every fix / re-roll until it PASSES" — a validation→fix→retry feedback loop for a publish-gating operation.

3 / 3

Progressive Disclosure

Single well-organized body with clearly labeled sections; the one external artifact (scripts/review_render.py) is a real bundled file referenced one level deep, with no nested reference chains.

3 / 3

Total

12

/

12

Passed

Description

85%

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 strong, specific description that states both what the skill does and when to use it, with concrete failure modes and an explicit trigger tied to recipe phases. The only weakness is trigger-term breadth: terms are specialized system jargon rather than broadly natural phrasings.

Suggestions

Broaden trigger terms with more natural phrasings (e.g. "use when a rendered video's spoken audio must match the approved script") so the description surfaces for users who don't name the recipe/atom internals.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Transcribes the finished render's AUDIO with Whisper", "word-diffs it against the approved spoken script", "gates set_final_render", and the specific block conditions (mis-voices a word, drops a phrase, comes back silent).

3 / 3

Completeness

Explicitly answers what (transcribe + word-diff + gate) and when ("Every ugc-video-formats recipe runs this after render and BEFORE set_final_render"; framed as a mandatory pre-publish gate).

3 / 3

Trigger Term Quality

Contains domain-relevant terms ("UGC video render", "set_final_render", "mis-voices a word") but they are recipe/system-specific jargon rather than broad natural variations a general user would say; coverage of common phrasings is narrow.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (UGC render transcript-vs-script gating tied to set_final_render in specific recipe families), uses third person throughout, and is unlikely to trigger for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.