render-stopmotion-hand-swatch-cycle

Assemble a stop-motion hand-swatch-cycle product-demo ad from a config — a sequence of still PLATES (one hand swiping a single-barrel product across a test surface, the barrel + swatch changing per plate while the hand, background, crop, and lighting stay locked) is PNG→mp4 loop-encoded at each plate's own stop-motion hold (fast motion frames 150–250ms, per-shade ~380ms, hero beats 1100–1800ms), concat-demuxed with HARD cuts into a silent master, closed on a Playwright HTML-rendered branded end card (serif tagline + sans subtitle + real logo SVG over a hero BG, never AI-rendered text), and muxed with a pre-sourced music track playing under the end card with a fade tail (no VO). This is the FREE deterministic assembly stage (loop-encode + concat-demux + end-card render + music mux); the master-anchor plate, shade plates, and end-card BG come from create-image-gpt-image-fal and the track from create-music-elevenlabs. Use for the stopmotion-hand-swatch-cycle format.

Quality

74%

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-stopmotion-hand-swatch-cycle/SKILL.md

Quality

Content

61%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 dense, well-structured contract-style body with specific parameters and a clear pipeline sequence, backed by real one-level-deep bundle files. It loses points for repeating the free-assembly framing multiple times and for offering no validation steps around the batch plate-encoding workflow.

Suggestions

Add a validation checkpoint to the workflow, e.g. after concat-demux verify the silent master's duration and plate count against the config (~16.6s expected) before appending the end card.

State the FREE/deterministic framing once (in the intro) and drop the restatements in the Run section and the final Contract bullet.

Convert bundle mentions into markdown links (e.g. [PIPELINE.md](scripts/PIPELINE.md)) and trim Contract bullets that duplicate scripts/README.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight, information-dense bullets, but the FREE/deterministic framing is repeated three times ('This capability is the FREE, deterministic assembly', 'This is the FREE, deterministic assembly stage — it spends nothing', 'FFmpeg composite, deterministic, FREE') and the frame-swap/crossfade point is made twice, so it could be noticeably tightened.	3 / 5
Actionability	Concrete command fragments ('ffmpeg -loop 1 -t <pose_hold_ms>', 'ffmpeg -f concat') and precise parameters (1080×1920 @ 30fps crf18, volume ≈0.4, fade over the last ~0.5s) make the guidance mostly executable, but no complete runnable command for any stage is given — minor gaps rather than missing key details.	4 / 5
Workflow Clarity	The sequence (loop-encode each plate → concat-demux → append end card → mux music) is coherent, but there are no validation or verification checkpoints anywhere in what is a batch operation (loop-encoding ~24+ plates), which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The body is a well-organized overview that clearly signals three real, one-level-deep bundle references ('scripts/config.example.json is the worked example', 'scripts/PIPELINE.md maps every config block', 'scripts/README.md documents the free assembly'), with the minor gaps that references are prose mentions rather than links and the Contract section partially duplicates scripts/README.md content.	4 / 5
	Total	14 / 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.

A highly specific, well-bounded description that clearly states what the skill does and cleanly separates it from sibling paid capabilities. Its weakness is triggering: the only 'Use for' hook is the internal format name, and jargon-dense phrasing crowds out the natural phrases a user would actually say.

Suggestions

Broaden the 'Use for' clause with scenario-based triggers users would naturally say, e.g. 'Use when the user wants a stop-motion product demo ad, a swatch-cycle shade video, or the stopmotion-hand-swatch-cycle format.'

Trim technical jargon in the opening (PLATES, concat-demuxed, loop-encoded) and surface one or two plain-language synonyms like 'stop-motion swatch video' or 'shade-cycling product demo' so natural-language matching works.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete, comprehensive actions — 'PNG→mp4 loop-encoded at each plate's own stop-motion hold', 'concat-demuxed with HARD cuts into a silent master', 'Playwright HTML-rendered branded end card', 'muxed with a pre-sourced music track' — covering the full assembly pipeline with no gaps.	5 / 5
Completeness	The 'what' is explicit and detailed, and a 'Use for...' clause is present, so it is not capped at 3; but the 'when' rests solely on the exact format name with no scenario-based trigger phrases, matching the anchor where 'when' could be more explicit rather than the fully-triggered 5 anchor.	4 / 5
Trigger Term Quality	Some relevant natural keywords appear ('stop-motion', 'product-demo ad', 'swatch', 'end card', 'music track'), but the only explicit trigger is 'Use for the stopmotion-hand-swatch-cycle format' — the internal format name — and common user-side variations ('swatch video', 'stop-motion product video', 'beauty shade demo') are absent amid heavy technical jargon (PLATES, concat-demux, loop-encode).	3 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — the FREE deterministic assembly stage of one specific ad format — and explicitly demarcates the paid sibling capabilities ('create-image-gpt-image-fal', 'create-music-elevenlabs'), so it is unlikely to trigger for the wrong 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-stopmotion-hand-swatch-cycle/SKILL.md
Commit: cc3e518

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.