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

77%

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

70%

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

A well-structured, clearly sequenced assembly contract with strong progressive disclosure to real bundle files and good verification checkpoints. It loses points on conciseness (repeated emphasis/restating) and actionability (inline flags but no executable code, and referenced runner scripts are absent from the bundle).

Suggestions

Ship the referenced runner scripts (build_v4.py, render_cards.py, composite_cards.py, build_master.py, product-card.html.tmpl) in scripts/ or replace the prose with one copy-paste-ready ffmpeg command chain per assembly stage so the guidance is executable as written.

De-duplicate the assembly description across the intro, Run, and Contract sections — keep the contract as the single authoritative list and trim the restated prose to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no explaining what ffmpeg/libass is), but the 'SEPARATE'/'FREE'/'PAID' emphasis and the same assembly description are restated across the intro, Run, and Contract sections, so it could be tightened to earn every token.	2 / 3
Actionability	Gives concrete inline flags and values ('-c:v libx264 -crf 20', '-loop 1 -t <dur>', 'loudnorm I=-14', '3 words/cue, ~3.0% font, ~20% margin') but no copy-paste executable code blocks, and the named runner scripts (build_v4.py, render_cards.py, composite_cards.py, build_master.py, product-card.html.tmpl) are not present in the bundle.	2 / 3
Workflow Clarity	Presents a clear ordered sequence (VO→Whisper→re-cut/concat→cards→mix→captions→end card) with explicit verification checkpoints ('Verify each clip's duration', 'PDP-verify every tagline', cutout must match the REAL product) and error-recovery hints (retry --tier fast on 422, trim Seedance drift in Phase 4).	3 / 3
Progressive Disclosure	The body is a concise overview pointing one level deep to real, clearly-signaled 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 in scripts/.	3 / 3
	Total	10 / 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, well-scoped description that clearly states what the skill does and when to use it, with strong distinctiveness. Its main weakness is trigger-term quality: the natural-language entry points are narrow and surrounded by technical jargon.

Suggestions

Broaden the trigger clause beyond the exact format name — add natural phrasings a user would say, e.g. 'Use for GRWM (get-ready-with-me) beauty-demo ads, makeup/skincare routine videos, or the glassy-matte-grwm format.'

Move dense jargon (loudnorm I=-14, Whisper word-level timestamps, PDP-verified taglines) out of the trigger surface so the opening reads as a natural capability statement rather than a spec.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 're-cut to the VO word-starts, hard-concat, Playwright card render + card composite, VO plus music mix, caption burn, flat-lay end card' — with specific parameters like 'loudnorm I=-14' and '3-words/cue captions', matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (the full deterministic assembly pipeline) and when via the explicit trigger 'Use for the glassy-matte-grwm format', satisfying the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Contains some natural terms a user might say ('GRWM beauty-demo ad', 'glassy-matte-grwm') but the only trigger clause is the narrow 'Use for the glassy-matte-grwm format', and the rest is heavy jargon (ElevenLabs, Whisper word-level timestamps, loudnorm, PDP-verified) rather than common variations like 'get ready with me' or 'beauty routine video'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (multi-scene GRWM beauty-demo, SEPARATE VO-driven timeline) and is explicitly contrasted against ugc-grwm, making it unlikely to trigger for the wrong skill.	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-glassy-matte-grwm/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.