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.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/ugc-fixloop/SKILL.md

Quality

Content

87%

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

The body is lean, highly actionable, and well-organized with verified bundle references; the main gap is the absence of an explicit sequenced workflow tying the two scripts together with validation checkpoints.

Suggestions

Add a short numbered workflow (e.g., 1. vet the prompt, 2. render the replacement via create-video-fal, 3. stitch with stitch_replacement.py, 4. check the drift warning) to make the multi-step sequence and validation explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and command/example-driven with no basic-concept padding; brief design rationales ("lip-sync on talking beats is never touched", "Claude reviewing its own prompt is a weaker signal") earn their place by preventing misuse, matching the lean score 3 anchor.	3 / 3
Actionability	Provides fully executable, copy-paste-ready invocations for both scripts with complete argument tables and defaults (e.g., '--window-start 4.21 --window-end 8.75 --fit stretch', '--replace-beat 2'), matching the executable-code anchor.	3 / 3
Workflow Clarity	Each script's invocation is unambiguous and built-in validation signals exist (drift >0.15s warning, exit 3 fallback), but the multi-step vet→render-replacement→stitch sequence is implied rather than laid out as an explicit numbered workflow with checkpoints, so it does not reach score 3.	2 / 3
Progressive Disclosure	At roughly 50 lines with well-organized sections (Env/deps, two Run sections, All args) and bundle scripts referenced by name that exist in ./scripts/, it meets the under-50-lines well-organized-sections criterion for score 3.	3 / 3
	Total	11 / 12 Passed

Description

67%

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

The description is highly specific and distinctive but over-relies on internal jargon for trigger terms and omits an explicit 'Use when' clause, capping completeness and trigger quality at 2.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural user phrases (e.g., 'Use when fixing a bad clip in a single-take UGC master or vetting a Seedance prompt before render').

Replace internal jargon in the trigger portion ('GooseWorks openai-proxy', 'bills the Ads agent') with user-facing terms so the skill surfaces on natural requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("surgically re-render a bad window/beat", "GPT cross-model review a Seedance prompt", "Fetch it into a one-shot UGC recipe") with named tools (FFmpeg, openai-proxy), matching the multi-action anchor rather than the single-domain score 2.	3 / 3
Completeness	The "what" is explicit but there is no "Use when..." clause or equivalent trigger guidance, which the guidelines cap at 2; the "Fetch it into a one-shot UGC recipe" phrase is a how, not a when.	2 / 3
Trigger Term Quality	Contains some relevant terms (UGC, re-render, Seedance prompt) but is dominated by internal jargon ("GooseWorks openai-proxy", "bills the Ads agent", "single-take UGC master") a user would not naturally say, so it is not the natural-coverage score 3.	2 / 3
Distinctiveness Conflict Risk	Targets a narrow, clearly delineated niche (UGC fix-loop, Seedance prompt vetting) with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	10 / 12 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/capabilities/ugc-fixloop/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.