render-food-product-sizzle

Assemble a wordless macro-tabletop food-product sizzle ad from a config — normalize fps and SAR across ~4 photorealistic macro clips (hands tearing, flat lay, bite, box hero), concat them, apply a global anti-AI grain pass (eq plus hqdn3d plus noise), composite the audio (a non-diegetic instrumental music bed plus a couple of short diegetic SFX like a snap and a tear placed at measured cue points, loudnorm), composite a STATIC end card entirely in PIL (real logo PNG plus real product PNG plus a serif heritage headline plus a CTA — never AI-rendered text), and burn optional serif stat-callout pills at beats. This is the FREE deterministic assembly stage (normalized concat plus grain plus music and SFX mix plus PIL end card plus callouts); the macro keyframes, i2v clips, and music bed come from create-image-fal, create-video-fal, and create-music-elevenlabs. Use for the food-product-sizzle 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

72%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 lean, domain-dense body that earns its tokens with exact filter parameters, timing specifics, and real escape-hatch gotchas, and points to a verified, well-organized bundle. Its weakness is workflow shape: the multi-stage pipeline order is implicit and includes no validation checkpoints on the final master.

Suggestions

Make the assembly pipeline explicit as a numbered sequence (normalize/concat → grain pass → audio mix → end card append → callouts → mux) and add verification checkpoints, e.g. ffprobe the concat body to confirm scene count and duration before the grain pass, and check master duration and loudness after mux.

De-duplicate the 'FREE, deterministic / $0' framing and the paid-vs-free boundary, which are stated nearly identically in the intro and the Run section — state it once and reference it.

Name or inline the concrete ffmpeg/PIL commands for the composite (or explicitly point to the build script in scripts/) instead of describing the filter parameters in prose, so the Run section is copy-paste executable.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence — exact filter string 'eq=contrast=1.06:saturation=0.93,hqdn3d=1.5:1.5:3:3,noise=alls=8:allf=t+u', SFX durations (~120ms snap, ~180ms tear), and no generic-concept padding. It misses 5 because the 'FREE, deterministic / $0' framing and paid-vs-free boundary are repeated across the intro, Run, and Contract sections and could be trimmed.	4 / 5
Actionability	Provides concrete, executable specifics: the full grain-pass filter chain, the drawtext 'textfile=' + 'expansion=none' workaround for the raw '%' strftime hazard, SFX timing to measured cue points, and end-card layout. It is 'Mostly executable guidance; concrete code or commands with minor gaps' — the full ffmpeg command sequence for the composite lives in the bundle files rather than being inline or explicitly named.	4 / 5
Workflow Clarity	The pipeline order (normalize/concat → grain pass → SFX mix → music bed → end card → callouts → mux) is present but only implicit in the Contract bullet order, with no numbered sequence and no validation checkpoints — nothing like verifying clip count/duration after concat or master length/loudness after mux. This matches the score-3 anchor 'sequence present but checkpoints missing or implicit'; the score-4 anchor requires most checkpoints present.	3 / 5
Progressive Disclosure	A 67-line body with clear sections that signals its bundle files — 'scripts/config.example.json is the worked example', 'scripts/PIPELINE.md maps every config block to its source step', 'scripts/README.md documents the free assembly' — all of which exist and are one level deep. This matches the score-5 anchor of a clear overview with well-signaled, appropriately split references.	5 / 5
	Total	16 / 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 highly specific, boundary-conscious description that names every assembly action with concrete ffmpeg/PIL detail and explicitly separates the free assembly stage from its paid upstream capabilities. Its only weakness is a narrow trigger clause and missing common synonyms for the ad format.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions with tool-level specifics — 'normalize fps and SAR', 'concat them', 'apply a global anti-AI grain pass (eq plus hqdn3d plus noise)', 'composite the audio... loudnorm', 'composite a STATIC end card entirely in PIL', 'burn optional serif stat-callout pills' — comprehensively covering every assembly stage. It matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' rather than the score-4 anchor, which expects minor gaps in coverage; none are evident.	5 / 5
Completeness	The 'what' is exceptionally concrete, and the 'when' is explicit — 'Use for the food-product-sizzle format.' — so it clears the score-3 cap for a missing trigger clause. It does not reach 5 because the when clause is a single terse phrase without the concrete trigger scenarios (e.g. 'when the user asks for a sizzle ad or wants to assemble clips into a commercial') that the score-5 anchor exemplifies.	4 / 5
Trigger Term Quality	Includes natural domain phrases a user would say — 'food-product sizzle ad', 'photorealistic macro clips', 'music bed', 'SFX', 'end card'. It sits at 'Good keyword coverage; a few natural terms missing' rather than 5 because common synonyms like 'commercial', 'promo', 'CPG', or 'video ad' are absent, but it is well above the score-3 anchor (relevant keywords with missing variations).	4 / 5
Distinctiveness Conflict Risk	Clear niche with explicit boundary-drawing — 'the macro keyframes, i2v clips, and music bed come from create-image-fal, create-video-fal, and create-music-elevenlabs' — delineating this FREE assembly stage from its sibling paid capabilities. Trigger terms ('food-product-sizzle', 'sizzle ad') are distinct, so it matches the score-5 anchor 'Clear niche with distinct triggers; minimal conflict risk'.	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-food-product-sizzle/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.