render-flat-vector-explainer

Assemble the FREE steps of the flat-vector-explainer video format — a flat-illustration host character (who, where, tone, voice and music come from the recipe choices) walks a countable N-step product routine, one step per beat, and Remotion composites every chip/numeral/tagline/slate/CTA as an animated DOM overlay ON TOP of the Kling i2v character clips (text is NEVER baked into a keyframe — i2v warps type), the closing 'N products' grid is a PIL composite of the REAL product photos (not AI), full-sentence VO drives word-by-word burned captions over a VO-forward music bed, and the ~50s animated silent master is re-cut to a 30s deliverable FROM the animated master (never a static intermediate). Documentation-grade — ships config.example.json + PIPELINE.md + a README of the free assembly; the paid gen steps (keyframes, Kling i2v, VO, music) are separate capabilities the recipe orchestrates. Use for the flat-vector-explainer 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

78%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 well-structured, documentation-grade skill: lean body, clearly sequenced free-assembly steps with named validation checks, and accurate one-level-deep references to real bundle files that carry the executable detail. Main room for improvement is trimming the restated separation rules and surfacing the frame-diff failure/recovery loop in the body itself.

Suggestions

Fold the Contract's restated separations ('Text is an overlay, never baked', 'Any multi-SKU grid is PIL...') into the 'two non-negotiable separations' section once, letting the Contract just reference them, to cut duplicate tokens.

In the 30s-cut step, state the frame-diff failure condition and recovery inline (e.g. 'if the diff shows whole-outline glow you sliced a static intermediate — re-point at silent-master.mp4') rather than only 'frame-diff to prove localized motion'.

Add one minimal inline example of the Remotion DOM-overlay pattern (or a pointer to the exact PIPELINE.md section per step) so the overlay step is as immediately actionable as the audio and cut steps.

Dimension	Reasoning	Score
Conciseness	The body is dense but efficient — it assumes Claude knows ffmpeg/Remotion/PIL and delegates detail to scripts/README.md ('see `scripts/README.md` for the ffmpeg/Remotion/PIL detail'). Minor over-explanation remains: the 'two non-negotiable separations' are restated nearly verbatim in the Contract section ('Text is an overlay, never baked', 'Any multi-SKU grid is PIL of the real product webps'). Not 5: that redundancy could be trimmed; not 3: there is no concept-explainer padding.	4 / 5
Actionability	For an instruction-only (documentation-grade) skill the guidance is concrete: specific filters ('sidechaincompress', 'loudnorm I=-15', 'setpts <=1.6x'), output filenames ('finals/master-final.mp4', 'finals/master-final-30s-v1.mp4'), ordering ('burn captions LAST'), and gate checks ('TEST one scene before batching'), with executable detail one level deep in scripts/README.md. Not 5: the body's step summaries occasionally stop at direction ('composite chips... as animated DOM on top') without a copy-paste-ready command or minimal Remotion snippet inline.	4 / 5
Workflow Clarity	The sequence is clear and ordered (paid gen steps -> Remotion overlay -> PIL grid -> captions -> audio mix -> 30s cut), with validation present ('frame-diff to prove localized motion', 'TEST one scene before batching') and the README adding a mandatory QC checklist with a recovery loop ('re-point the cut at silent-master.mp4'). Not 5: the body itself names frame-diff but does not state what to do when it fails (whole-outline glow) — that feedback loop lives only in the README.	4 / 5
Progressive Disclosure	Clean overview-plus-references structure: the body is a lean map and each detail file is clearly signaled and real — 'see `scripts/README.md` for the ffmpeg/Remotion/PIL detail', `scripts/config.example.json` (the worked schema example), and `scripts/PIPELINE.md` (the field-to-script map) all exist in the bundle, one level deep, no nested-reference chains. Not 4: navigation is unambiguous and every referenced path resolves.	5 / 5
	Total	17 / 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.

The description is comprehensive and unambiguous about what the skill does and is highly distinct, with an explicit 'Use for...' clause. Its weaknesses are the very long, jargon-dense phrasing (Remotion/Kling/PIL internals users would not say) and trigger terms limited to the exact format name, missing natural synonyms like 'explainer video'.

Suggestions

Add natural trigger synonyms to the 'when' clause, e.g. 'Use when the user wants a flat-vector explainer video, animated product-routine video, or short DTC product explainer' rather than only the literal format name.

Trim pipeline internals (e.g. cfg values, 'eleven_v3 with-timestamps', 'sidechaincompress' detail) from the description — those belong in the body/README — to cut density and keep the description scannable.

Rewrite dense inline parentheticals like 'ON TOP of the Kling i2v character clips (text is NEVER baked into a keyframe — i2v warps type)' into a single crisp clause; the constraint itself can stay in the body's Contract.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions: 'Remotion composites every chip/numeral/tagline/slate/CTA as an animated DOM overlay', 'the closing "N products" grid is a PIL composite of the REAL product photos', 'full-sentence VO drives word-by-word burned captions', and 're-cut to a 30s deliverable FROM the animated master' — comprehensive and concrete coverage of what the capability does. Not 4: the actions are specific and cover assembly, compositing, captions, mixing, and re-cutting, not just several with minor gaps.	5 / 5
Completeness	The 'what' is explicit and detailed, and the 'when' is present as 'Use for the flat-vector-explainer format.' Not 5: the trigger clause is narrow — it fires only when the user already names the exact format, with no broader trigger phrasing (e.g. wanting a flat-vector explainer or short DTC product video); 'when' could be more explicit. Not 3: an explicit 'Use for...' clause does exist.	4 / 5
Trigger Term Quality	Relevant keywords exist ('flat-vector-explainer video format', 'explainer', 'product routine', 'Remotion'), but the natural user phrases are thin: no synonyms like 'explainer video', 'animated product video', or 'product demo', and much of the text is pipeline jargon ('Kling i2v', 'eleven_v3', 'cfg', 'molecule') users would never say. Not 4: the keyword coverage is not 'good with a few missing' — the common variations users would actually say are largely absent.	3 / 5
Distinctiveness Conflict Risk	The description carves out a highly specific niche (flat-vector N-step product-routine explainer with a Remotion-overlay-on-Kling-clips pipeline, real-photo PIL grid, animated-master re-cut) and explicitly disclaims the paid gen steps as separate capabilities — minimal overlap risk with generic video or image skills.	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-flat-vector-explainer/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.