render-3d-product-showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at loudnorm I=-16 (music-only, no VO). Ships the runnable build_endcard.py + build_masters.py; the rotation/macro clips are create-video-fal i2v seeded on a create-image-fal styled hero, the reveal is Veo3 i2v, and the bed is create-music-elevenlabs. Use for the 3d-product-showcase 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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/render-3d-product-showcase/SKILL.md

Quality

Content

72%

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

The body is exceptionally dense and free of filler, with well-organized sections pointing to real bundled references. It is held back by mix-chain guidance left in prose (not a literal FFmpeg command) and the absence of explicit validation checkpoints for the batch hard-concat assembly.

Suggestions

Add an explicit validation step to the Run sequence, e.g. after build_masters.py: 'ffprobe the master to confirm 720×1280, h264+aac, and duration == sum of beat windows; re-run if mismatched.'

Replace the prose FFmpeg mix description in the Contract with one literal, copy-pasteable command (or reference a script block) so the audio mix is fully executable like the end-card step.

Dimension	Reasoning	Score
Conciseness	Lean and dense with no filler or beginner-concept explanation — every line delivers a specific flag, parameter, or constraint (e.g. 'loudnorm I=-16 TP=-1.5 LRA=11', 'ffmpeg -sseof -0.1 … -frames:v 1'); it assumes Claude's competence throughout.	3 / 3
Actionability	Gives concrete CLI invocations with real flags, but they include placeholders ('--headline "…"', '<wordmark>') and the FFmpeg mix chain is described in prose ('afade in/out + loudnorm...', 'apad + atrimmed') rather than as a literal, copy-pasteable command.	2 / 3
Workflow Clarity	The two-step Run sequence and Contract section give a clear order, but there is no explicit validation/verification checkpoint for the batch 4-clip hard-concat (e.g. 'verify each beat is 720×1280 yuv420p before concat', 'confirm master duration == sum of beat windows'); the rubric caps batch/destructive operations at 2 when checkpoints are missing.	2 / 3
Progressive Disclosure	Clear overview sections with one-level-deep references to real bundled files that all exist — 'scripts/PIPELINE.md maps every config block', 'scripts/README.md documents the assembly', 'scripts/config.example.json is the worked example' — well signaled and easy to navigate.	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.

The description is highly specific and complete, naming concrete actions, exact codec parameters, and the runnable scripts, with an explicit 'Use for' trigger. Its only weakness is trigger-term naturalness: the trigger is a niche format name and the text leans on internal tool/capability identifiers rather than user-facing language.

Suggestions

Add plain-language trigger phrasing a user might actually say, e.g. 'Use when the user asks to render a 3D product showcase ad, a 3D product video, or a spinning-hero product spot.'

Reduce reliance on internal capability IDs (create-video-fal, create-music-elevenlabs) in the description; surface them in the body instead so the description stays readable to anyone routing the skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with exact parameters — 'hard-concatenated in order', 'closed on a deterministic Playwright brand end card', 'mixed under one instrumental bed at loudnorm I=-16' — and names the specific runnable scripts and tools.	3 / 3
Completeness	Explicitly answers both what ('Assemble a premium 3D product-showcase ad...') and when ('Use for the 3d-product-showcase format'), with the explicit trigger clause satisfying the 'Use when...' requirement.	3 / 3
Trigger Term Quality	Has a relevant trigger ('Use for the 3d-product-showcase format') and tool keywords, but the natural-user phrasing is thin — it leans on internal capability names (create-video-fal, create-image-fal, Veo3, create-music-elevenlabs) rather than terms a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	A clear, narrow niche (3d-product-showcase assembly) with a distinct format-name trigger; unlikely to fire for unrelated skills.	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-3d-product-showcase/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.