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

87%

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

100%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.

An efficient, fully actionable skill body: concrete commands, a clearly sequenced render pipeline, an explicit stale-output validation warning, and clean one-level disclosure to its three scripts. It earns top marks across all content dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — every section (Run, Scripts, Contract) carries load-bearing detail like exact args, dimensions, and the stale-PNG gotcha, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	It gives copy-paste-ready command lines with concrete args and flags ('fetch_icons.py --run-dir <run>', 'compose_master.py ... --no-music'), names inputs/outputs, and specifies the FFmpeg reveal mechanism ('enable=\'gte(t,T)\''), covering the common cases including a silent preview variant.	5 / 5
Workflow Clarity	A clear sequenced three-step pipeline (fetch icons → build overlays → compose master) with an explicit validation checkpoint: the Contract warns to always re-run build_overlays.py before compose because the compositor silently reuses stale PNGs, which is exactly the validate-before-proceed guard a media-rendering skill needs.	5 / 5
Progressive Disclosure	A single well-organized SKILL.md with clear sections (Run, Scripts, Contract) and one-level-deep pointers to the three scripts in scripts/ that are each summarized inline; no nested references and nothing buried, appropriate for a focused single-purpose skill.	5 / 5
	Total	20 / 20 Passed

Description

75%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 highly specific, distinctive description that clearly scopes a narrow free-rendering niche and lists concrete actions. Its main weakness is trigger-term quality: it relies on format-internal jargon and offers only one narrow 'Use for…' clause rather than natural user-facing triggers.

Suggestions

Add natural-language trigger phrases users would actually say (e.g. 'Use when rendering the proof-points overlay ad, compositing score pills onto a video, or building a 10/10 UGC review ad') alongside the existing 'Use for the overlay-proof-points format' clause.

Include a synonym or two for 'proof-points overlay' so the description matches how requesters phrase the task, not just the internal format name.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — building PIL pill overlays (score header, sub pill, 3-4 proof pills), compositing onto a base clip in a diagonal cascade, and muxing the music bed — with specifics like 1080x1920 9:16 and config.json drive, giving comprehensive coverage.	5 / 5
Completeness	It clearly states what it does (build and composite overlays, mux music) and includes a 'Use for the overlay-proof-points format' clause answering when, but the when is narrow and could be more explicit about the natural situations that would call for it.	4 / 5
Trigger Term Quality	It names the domain ('overlay-proof-points format', 'UGC video ad') but leans on internal jargon ('proof pills', 'cascade', 'pixel-crisp') rather than natural user phrases; only the one 'Use for the overlay-proof-points format' clause approaches a natural trigger, missing common synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	The description carves a clear niche — deterministic free PIL/FFmpeg overlay rendering for a specific ad format, explicitly scoping out paid base-clip and music capabilities — so it is unlikely to trigger for the wrong skill.	5 / 5
	Total	17 / 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/capabilities/render-proof-points-overlay/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.