render-glassy-matte-grwm

Assemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 products step by step while a SEPARATE ElevenLabs voiceover narrates and every scene cut is snapped to the VO's product-name word-starts (Whisper word-level timestamps), then ~5 Playwright product overlay cards (real PDP-verified taglines) are composited onto the master each on its product-NAME word-start, the SEPARATE VO is mixed on top of a ducked music bed at loudnorm I=-14, clean-white 3-words/cue captions are burned, and the video closes on a flat-lay end card. This is the FREE deterministic assembly stage (re-cut to the VO word-starts, hard-concat, Playwright card render + card composite, VO plus music mix, caption burn, flat-lay end card); the VO, scene clips, product cutouts, and music come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the glassy-matte-grwm format.

Quality

78%

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/render-glassy-matte-grwm/SKILL.md

Quality

Content

72%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 content is technically actionable and well-structured with clean progressive disclosure to real bundle files. Its main gaps are the absence of explicit output-validation checkpoints in a batch render pipeline and some redundant emphatic repetition across sections.

Suggestions

Add an explicit validation step after assembly (e.g., probe the master with ffprobe to confirm ~32s/1080×1920/30fps and that all 5 cards are visible on their word-start beats) before declaring the render complete.

Dedupe the repeated 'SEPARATE VO' and 'FREE' emphasis across the intro, Run, and Contract sections so each point is stated once authoritatively.

Provide at least one end-to-end example ffmpeg command chain (or a reference to one in scripts/) so the flag fragments combine into copy-paste-ready guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (ffmpeg flags, loudnorm, libx264 without explaining them), but repeats emphatic markers ('SEPARATE VO', 'FREE') across the intro, Run, and Contract sections, which could be trimmed without losing clarity.	4 / 5
Actionability	Provides concrete, specific guidance — '-c:v libx264 -crf 20', '-loop 1 -t <dur>', 'loudnorm I=-14', '3 words/cue, ~3.0% font, ~20% margin' — but offers flag fragments rather than complete copy-paste-ready pipeline commands, leaving minor gaps.	4 / 5
Workflow Clarity	A clear ordered pipeline is implied (Whisper VO → snap cuts → hard-concat re-encode → render+composite cards → mix VO over music → burn captions → append end card) with strong guardrails, but there are no explicit validate→fix→retry checkpoints for this batch render, which caps the score per the destructive/batch validation rule.	3 / 5
Progressive Disclosure	The body is an overview with well-signaled one-level-deep references to real bundle files — 'scripts/config.example.json is the worked example', 'scripts/PIPELINE.md maps every config block', 'scripts/README.md documents the free assembly' — all of which exist, with content appropriately split into the scripts/ directory.	5 / 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.

The description is highly specific and distinctive, naming concrete assembly actions and a clear format trigger. Its main weakness is the 'when' clause being format-narrow and the heavy technical jargon limiting natural trigger-term coverage.

Suggestions

Broaden the 'Use for...' clause to describe the user situations that call for this skill (e.g., 'Use when assembling a multi-scene GRWM/get-ready-with-me beauty ad driven by a separate voiceover') rather than only naming the format.

Add a couple of natural user synonyms (e.g., 'get-ready-with-me', 'beauty routine ad') alongside 'GRWM' to improve trigger-term recall.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assembly actions — 'snap scene cut to the VO's product-name word-starts', '~5 Playwright product overlay cards...composited onto the master', 'VO is mixed on top of a ducked music bed at loudnorm I=-14', 'captions are burned', 'flat-lay end card' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly states 'what' (the full deterministic assembly pipeline) and includes an explicit trigger clause 'Use for the glassy-matte-grwm format.', but the 'when' is format-narrow and could be more explicit about the scenarios that call for it.	4 / 5
Trigger Term Quality	Includes natural user-facing terms like 'GRWM beauty-demo ad' and 'glassy-matte-grwm format', but the surrounding vocabulary (ElevenLabs, Playwright, Whisper, loudnorm) is heavily technical and a few natural synonyms a user might say are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — the glassy-matte-grwm multi-scene VO-driven beauty format — distinct from sibling skills like ugc-grwm, with trigger language specific enough to minimize wrong-skill activation.	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-glassy-matte-grwm/SKILL.md
Commit: 2523432

Reviewed: 13 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.