render-brand-identity-reveal

Render a 'brand identity reveal' video from a config — a single poster frame in a real, softly-lit space (real wall, soft-focus plant in the corner, dappled leaf shadow, illuminated poster) whose artwork HARD-CUTS through ~10 on-brand poster mockups (hero product, IG post, hanging banners, sticker sheet, logo lockup, poster, two lifestyle stills, packaging, big icon) then holds on a brand end card. The environment plate is one create-image-fal generation; the mockups are real-DOM HTML frame-stepped via Playwright, perspective-composited into the detected frame quad with the plate's real leaf-shadow multiplied back onto each poster (reads as behind glass), sequenced by FFmpeg. Deterministic assembly, FREE (the plate comes from create-image-fal, the bed from create-music-elevenlabs), music bed only and approved brand copy only. Use for the brand-identity-reveal format.

Quality

85%

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

93%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.

The body is a lean, fully-executable overview with a clear command sequence and well-signaled one-level references to real bundle files; its only gap is relying on manual 'watch' inspection rather than an explicit validate-retry loop for the batch render.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence throughout — it never explains what Playwright, FFmpeg, or perspective-warping are, and every section (Three layers, Inputs, Workflow, Rules, Failure Modes) earns its place.	5 / 5
Actionability	The workflow block is a copy-paste-ready bash sequence with exact commands, arguments, and run-directory layout, and each script's purpose is tied to a concrete output, covering the common case end to end.	5 / 5
Workflow Clarity	The five steps are clearly sequenced with per-step commands and a 'watch the master' inspection checkpoint plus a Failure Modes recovery list, but verification is manual inspection rather than an explicit validate-fix-retry feedback loop for this batch render pipeline.	4 / 5
Progressive Disclosure	The body is a concise overview that signals one-level-deep references to real bundle files (scripts/PIPELINE.md, scripts/config.example.json), both of which exist, keeping detail out of SKILL.md and navigation easy.	5 / 5
	Total	19 / 20 Passed

Description

76%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.

The description is highly specific and distinct, naming concrete actions and a clear niche, but its trigger guidance is a single format label rather than a spread of natural trigger phrases, which caps completeness and trigger-term quality.

Suggestions

Expand the 'when' clause beyond 'Use for the brand-identity-reveal format' to list situations and synonyms users would naturally say, e.g. 'Use when rendering a brand reveal video, an identity-launch teaser, or a poster-mockup reel.'

Add natural trigger keywords and surface forms (e.g. 'brand reveal', 'identity reveal video', 'poster mockup montage') so the description matches varied user phrasings.

Consider trimming the long inline mockup enumeration in the description to keep the what-clause readable while preserving the concrete actions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — HARD-CUTS through named mockup types (hero product, IG post, hanging banners, sticker sheet, logo lockup, packaging, big icon), perspective-compositing with shadow multiply, FFmpeg sequencing — covering the full pipeline comprehensively.	5 / 5
Completeness	Clearly and exhaustively answers 'what' (the full render signature and assembly), and includes an explicit 'when' via 'Use for the brand-identity-reveal format', but the trigger clause is present without enumerating the situations or synonyms that would push it to 5.	4 / 5
Trigger Term Quality	Contains relevant natural phrases ('brand identity reveal', 'poster mockups', 'brand end card', 'video from a config') but the trigger guidance is a single format name ('Use for the brand-identity-reveal format') with limited synonyms or surface-form variations a user might say.	3 / 5
Distinctiveness Conflict Risk	Occupies a very specific niche — a single named video format with a distinctive poster-in-real-space signature — making it unlikely to fire for any other 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-brand-identity-reveal/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.