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 acoustic 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

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-food-product-sizzle/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.

A lean, technically dense body with clean progressive disclosure to real bundled references, but it stops short of full actionability by omitting any complete executable command and by pointing at runner scripts that are not themselves bundled. Workflow clarity is also held at 2 by the absence of any output-validation checkpoint.

Suggestions

Add at least one complete, copy-paste ffmpeg filter_complex command (or a bundled build_master_v2.sh) so the assembly is executable, not just described.

Include a validation checkpoint after the mux step (e.g., ffprobe the master for 1080x1920, ~14s, h264+aac, and confirm audio bed is non-silent under the end card) to lift workflow_clarity.

Bundle or inline the referenced runner scripts (make_end_card.py, make_sfx.sh, build_master_v2.sh) so the actionability gap between the config/pipeline map and a runnable build is closed.

Dimension	Reasoning	Score
Conciseness	Dense and technical with no concept padding (no "what is ffmpeg/PIL" exposition) and every line carrying specifics; not a 2 because it assumes Claude's competence and avoids unnecessary explanation, despite mild restating of the "FREE deterministic" framing.	3 / 3
Actionability	Provides concrete fragments (the exact grain filter chain, drawtext textfile= + expansion=none trick, h264+aac 1080x1920 output) but no complete executable command, and the actual runner scripts it points to are not bundled; not a 3 because nothing is copy-paste ready and not a 1 because real parameters are given.	2 / 3
Workflow Clarity	The assembly sequence is clearly ordered (concat, grain, audio composite, end card, callouts, mux) but no validation/verification step is given for a render/mux operation, capping it at 2 per the batch-operation guideline; not a 1 because the sequence is explicit.	2 / 3
Progressive Disclosure	The body is an overview with well-signaled, one-level-deep references to real bundled files (scripts/config.example.json, scripts/PIPELINE.md, scripts/README.md), all verified present; not a 2 because navigation and split are clean.	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.

A highly specific, third-person description that clearly states what the skill does and when to use it, with a distinct niche unlikely to conflict. Its main weakness is trigger-term quality: the natural keywords are thin relative to a heavy load of technical jargon a user would rarely say verbatim.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("normalize fps and SAR", "concat them", "apply a global anti-AI grain pass", "composite the audio", "composite a STATIC end card entirely in PIL", "burn optional serif stat-callout pills"), matching the multiple-specific-actions anchor; not a 2 because it is comprehensive rather than partial.	3 / 3
Completeness	Clearly answers what (the full assembly description) and gives an explicit when ("Use for the food-product-sizzle format."), so it is not capped at 2; not below 3 because both what and when are explicit.	3 / 3
Trigger Term Quality	Carries some natural terms ("food-product sizzle ad", "sizzle", "food-product-sizzle format") but is dominated by technical jargon ("macro-tabletop", "i2v clips", "hqdn3d", "loudnorm", "diegetic SFX", "SAR") a user would not naturally say and misses common variations; not a 3 due to thin natural-keyword coverage.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (wordless macro-tabletop food-product sizzle ad assembly) with distinct triggers unlikely to fire for other skills; not a 2 because it is unambiguous rather than overlapping.	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-food-product-sizzle/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.