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

68%

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

53%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 technically rich body with concrete filter strings and parameters and a clean one-level-deep reference structure into the bundled scripts. Its weaknesses are notable Run/Contract redundancy, missing bundled runner scripts and an assembled command, and no explicit validation checkpoints for the multi-step composite.

Suggestions

Bundle the referenced runner scripts (build_master_v2.sh, make_end_card.py, make_sfx.sh) or inline one complete, executable ffmpeg filter_complex command so the assembly can be run end-to-end from what ships in the skill.

Add explicit validation checkpoints to the workflow (e.g. verify the concat produced the expected body length and that the end card PNG exists before muxing) to lift workflow_clarity above the batch-operation cap of 3.

De-duplicate the 'Run' and 'Contract' sections — fold the shared grain/SFX/end-card specifics into one place and keep the other as the terse contract list — to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and packed with concrete parameters, but the 'Run' and 'Contract' sections restate each other (grain filter, SFX cues, end-card details) and several rationale asides ('A diffusion model garbles a wordmark and the packaging') could be trimmed.	3 / 5
Actionability	Gives real, copy-pasteable specifics — the exact grain filter string, SFX durations and cue points, the drawtext textfile/expansion=none trick, and the output spec — but provides no assembled end-to-end ffmpeg command, and the referenced runner scripts (build_master_v2.sh, make_end_card.py, make_sfx.sh) are not bundled in ./scripts/, leaving key execution detail missing.	3 / 5
Workflow Clarity	The assembly sequence (normalize/concat → grain → audio composite → end card → callouts → mux) is clear, but for a multi-step batch media operation there are no explicit validate-then-proceed checkpoints in the body, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Good structure with well-signaled, verified one-level-deep references to scripts/config.example.json, scripts/PIPELINE.md, and scripts/README.md (all present), but the dense 'Contract' section arguably carries detail that could live in a referenced file.	4 / 5
	Total	13 / 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, well-scoped description that names many concrete assembly actions and clearly distinguishes this free assembly stage from its paid upstream capabilities. The main weakness is a single, somewhat thin 'Use for...' trigger clause rather than a richer set of natural trigger phrases.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete assembly actions — 'normalize fps and SAR', 'concat them', 'apply a global anti-AI grain pass (eq plus hqdn3d plus noise)', 'composite the audio', 'composite a STATIC end card entirely in PIL', 'burn optional serif stat-callout pills' — giving comprehensive coverage of what the stage does.	5 / 5
Completeness	Clearly answers 'what' with a long action list and answers 'when' with 'Use for the food-product-sizzle format', but the trigger clause names only a single format rather than enumerating concrete user-mentionable scenarios, so it sits just below the top anchor.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('food-product sizzle', 'sizzle ad', 'macro clips') plus the format name, but is somewhat technical and misses common synonyms like 'sizzle reel' or 'commercial'; good but not exhaustive coverage.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — the FREE deterministic assembly stage — and explicitly distinguishes its inputs from the paid capabilities (create-image-fal, create-video-fal, create-music-elevenlabs), giving 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: 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.