render-proof-points-overlay

Build the deterministic PIL pill overlays for a 'perfect-score + proof-points' UGC video ad (white 10/10 score header with a medal + orange sub with a finger-down + 3-4 green-check proof pills) and composite them onto a base clip in a diagonal L->R->L->R cascade, then mux the music bed into master-final.mp4. Config-driven (config.json), 1080x1920 9:16, FREE and deterministic (no paid calls, text stays pixel-crisp). Use for the overlay-proof-points format; the base clip + music come from separate paid capabilities.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%

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

A lean, highly actionable overview with a clean run sequence and well-organized references to real bundle scripts. The main gap is the absence of an explicit output-validation/verification checkpoint in the render pipeline.

Suggestions

Add a verification step after compose_master.py, e.g. probe the output with ffprobe to confirm 1080x1920@30 and audio stream presence before declaring master-final.mp4 done.

Make the build->compose ordering guard an explicit numbered checkpoint (e.g. "3. Verify PNGs are freshly built before composing") so the silent-stale-PNG gotcha reads as a validation gate rather than a footnote.

Dimension	Reasoning	Score
Conciseness	The body is dense operational detail (Twemoji PNG codepoints, FFmpeg filter expressions, crf23/maxrate12M) and assumes Claude's competence without explaining what PIL/FFmpeg are, matching the lean score-3 anchor; not score 2 because there is no padded explanatory filler.	3 / 3
Actionability	The Run section gives a concrete, copy-pasteable command sequence with flags ("fetch_icons.py --run-dir <run> ; build_overlays.py --config config.json --out-dir <run>/generated/overlays ; compose_master.py --config config.json --run-dir <run>"), matching the fully-executable score-3 anchor.	3 / 3
Workflow Clarity	The three-step sequence is clearly listed and includes an explicit guard ("Always re-run build_overlays.py before compose_master.py"), but there is no explicit validation/verification step or validate->fix->retry feedback loop for the re-encoding pipeline, so it does not reach the score-3 anchor.	2 / 3
Progressive Disclosure	The body is a concise overview organized into Run/Scripts/Contract sections that point to real one-level-deep bundle scripts (fetch_icons.py, build_overlays.py, compose_master.py) present in ./scripts/, matching the well-signaled one-level-deep score-3 anchor.	3 / 3
	Total	11 / 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 highly specific, third-person description that concretely names its actions and an explicit use-trigger, with a clear distinctive niche. Its only weakness is that the trigger term is a proprietary format name rather than phrasing a user would naturally say.

Suggestions

Add a more natural-language trigger alongside the format name, e.g. "Use when rendering the proof-points / 10-out-of-10 review-score overlay for a UGC ad, or when compositing score-pill graphics onto a base clip."

Surface one or two common user phrasings (e.g. "perfect-score ad", "review-score pills") so the trigger matches how users actually request the skill.

Dimension	Reasoning	Score
Specificity	"Build the deterministic PIL pill overlays... composite them onto a base clip... mux the music bed into master-final.mp4" lists multiple specific concrete actions (render pills, composite, mux), matching the score-3 anchor rather than the partial score-2 anchor.	3 / 3
Completeness	It clearly states what it does (build/composite/mux) and provides an explicit when-clause ("Use for the overlay-proof-points format; the base clip + music come from separate paid capabilities"), satisfying both what AND when; not score 2 because the trigger guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	The explicit trigger "Use for the overlay-proof-points format" plus domain terms (UGC video ad, proof pills, 10/10 score header) give some relevant keywords, but the trigger leans on a coined internal format name rather than natural terms a user would actually say, so it does not reach the broad natural-term coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	The niche is extremely specific (proof-points UGC ad overlay pipeline with a diagonal cascade), with distinct triggers unlikely to fire for any other skill, matching the clear-niche score-3 anchor.	3 / 3
	Total	11 / 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/render-proof-points-overlay/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.