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

81%

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

80%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 highly actionable, well-structured skill body that hands Claude ready-to-run commands and delegates depth to verified bundle files. Its one real gap is the absence of an explicit validate/verify checkpoint in the batch assembly workflow.

Suggestions

Add an explicit validation checkpoint before the final master mix — e.g. after hard-concat, verify each beat trimmed correctly and the concat produced the expected frame count/duration before mixing the bed.

De-duplicate the 'FREE / deterministic / $0' framing so it appears once (in the Run intro) rather than recurring across the Run and Contract sections.

Add a short error-recovery note for the known fragile step (Playwright browser build / PW_CHROME) so Claude has a feedback loop rather than only a fallback flag.

Dimension	Reasoning	Score
Conciseness	Mostly lean and command-driven with no padding about basic video concepts, but the 'FREE, deterministic assembly / spends nothing / $0' refrain recurs several times across the Run and Contract sections and could be tightened.	4 / 5
Actionability	Provides copy-paste-ready commands with full flags — `build_endcard.py --bg ... --headline ... --wordmark ... --out ...`, `build_masters.py --config ... --clips ... --endcard ... --music ... --out ...` — plus concrete ffmpeg params (-an, scale+pad to 720×1280, 24fps, yuv420p, crf 18, concat demuxer, loudnorm I=-16 TP=-1.5 LRA=11).	5 / 5
Workflow Clarity	The two-step Run sequence and the Contract constraints are clear, but this batch media-build has no explicit validation or verification checkpoint (e.g. confirm clips exist, verify concat/output), which caps workflow clarity at 3 per the batch-operations guideline.	3 / 5
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references to real, verified bundle files — `scripts/config.example.json`, `scripts/build_endcard.py`, `scripts/build_masters.py`, `scripts/PIPELINE.md`, `scripts/README.md` — all present in ./scripts/.	5 / 5
	Total	17 / 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 dense, specific description that concretely enumerates the assembly pipeline and ships runnable scripts, with an explicit (if terse) use-for trigger. Its main limitation is jargon-heavy phrasing and a single narrow trigger clause.

Suggestions

Expand the 'Use for...' clause into a fuller trigger sentence (e.g. 'Use when the user wants to render or assemble a 3D product-showcase ad, re-cut an existing showcase, or stitch delivered beats into a master') to broaden natural trigger coverage.

Move the internal tool-chain jargon (create-video-fal, Veo3 i2v, create-music-elevenlabs, loudnorm I=-16) out of the description or compress it, since these are implementation details unlikely to be a user's natural request phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — covering the full assembly pipeline comprehensively.	5 / 5
Completeness	Clearly states what it does (assemble the showcase from a config) and when to use it ('Use for the 3d-product-showcase format'), but the 'when' clause is a single terse format reference rather than a richer set of trigger phrases.	4 / 5
Trigger Term Quality	Captures natural phrasing a user would say ('3D product-showcase ad', 'product-showcase format') with an explicit 'Use for the 3d-product-showcase format' trigger, though it leans on technical jargon (create-video-fal, Veo3 i2v, loudnorm) and lacks synonyms/extensions.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — the deterministic $0 assembly stage of one specific format — with a narrow, format-scoped trigger that makes overlap with other skills minimal.	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-3d-product-showcase/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.