render-mosaic-grid-reveal

Render a 'mosaic-grid-reveal' video from a config — a real-DOM FULL-BLEED N×N mosaic of real product tiles that pops in one tile at a time (scatter order, ease-out-back overshoot), the grid clears, then the brand wordmark builds line-by-line followed by a sub-label, tagline, and CTA; frame-stepped via Playwright and encoded with FFmpeg — deterministic assembly, FREE (the music bed comes from create-music-elevenlabs), so the wordmark, tile captions, and CTA stay pixel-crisp. Use for the mosaic-grid-reveal format.

Quality

83%

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

76%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 well-organized, highly actionable body with copy-paste commands, a concrete config schema, and a real worked example. Its main gaps are the complete absence of validation/verification checkpoints in a batch rendering pipeline (capping workflow clarity) and some redundancy from restating the description in the intro.

Suggestions

Add validation checkpoints to the Run workflow, e.g. after build_html.py confirm duration_sec was written back and non-zero, and after render.py verify the master's frame count/duration before muxing (re-run render if it mismatches).

Trim the opening paragraphs that repeat the frontmatter description verbatim, and move demo-specific asides ('the demo used a warm off-white', 'the demo used light upbeat marimba') into scripts/config.example.json or a short example section.

Consider moving the dense per-field Inputs listing into a references/config-fields.md file, keeping only the essential fields inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence (no explanation of known concepts), but the opening two paragraphs largely restate the frontmatter description and parenthetical asides like 'the demo used a warm off-white' add tokens that could be trimmed, fitting the 'efficient; minor instances of over-explanation' anchor rather than the every-token-earns-its-place anchor at 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the whole pipeline ('python3 scripts/build_html.py --config config.json --out hyperframe.html', 'python3 scripts/render.py ...', and the complete ffmpeg mux command), plus a concrete config schema and a real filled example at scripts/config.example.json, matching the top anchor.	5 / 5
Workflow Clarity	The build_html → render → mux sequence is clearly laid out, but there are no validation or verification checkpoints anywhere (no check that duration_sec was written back, no output verification), and frame-stepped rendering is a batch operation over many frames — the rubric caps workflow clarity at 3 for batch workflows lacking validation.	3 / 5
Progressive Disclosure	Good structure with clear sections (Inputs, Choices, Run, Rules) and a clearly signaled, real reference to scripts/config.example.json that is one level deep; however the dense inline Inputs config reference and ~62-line body could be better split, fitting anchor 4 rather than the clean overview with fully separated references at 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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, well-scoped description that comprehensively describes what the skill renders and how (real-DOM, Playwright frame-stepping, FFmpeg encoding), with an explicit 'Use for...' trigger clause. The trigger phrasing is narrow — essentially only the format name — which slightly limits natural-term coverage and the explicitness of the 'when'.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions — 'Render a mosaic-grid-reveal video from a config', tiles that 'pop in one tile at a time (scatter order, ease-out-back overshoot)', grid clears, wordmark 'builds line-by-line', 'frame-stepped via Playwright and encoded with FFmpeg', music bed from create-music-elevenlabs — giving comprehensive, not just 'several', specific actions, which matches the top anchor rather than the 'minor gaps' anchor at 4.	5 / 5
Completeness	It has both a very detailed 'what' and an explicit trigger clause ('Use for the mosaic-grid-reveal format.'), but the 'when' is a single narrow phrase and could be more explicit with additional concrete trigger situations, matching anchor 4 rather than the fully-explicit anchor 5; it is above 3 because explicit 'Use when' guidance is present.	4 / 5
Trigger Term Quality	Good keyword coverage ('mosaic-grid-reveal', 'video', 'grid', 'tiles', 'wordmark', 'CTA', 'Playwright', 'FFmpeg') but it leans on the single format name and misses natural synonyms a user might say (e.g. 'product showcase video', 'brand grid video'), fitting the 'good coverage, a few natural terms missing' anchor rather than the comprehensive-synonym anchor at 5.	4 / 5
Distinctiveness Conflict Risk	A uniquely named, hyper-specific niche format ('mosaic-grid-reveal') with distinct triggers and essentially zero overlap risk with other skills, matching the 'clear niche with distinct triggers' anchor rather than the 'minor overlap risk with closely related skills' anchor at 4.	5 / 5
	Total	18 / 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-mosaic-grid-reveal/SKILL.md
Commit: cc3e518

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.