Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gooseworks-ai/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 seri
Passed 21 of 21 test cases with the skill, and 9 of 21 without it.
and 12 more in the full report
13 fixed9 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
What final video resolution and aspect ratio should be configured when outputting the master render for our CPG food product sizzle ad?
| Checked | Without skill | With skill |
|---|---|---|
| Outputs the final video at 1080x1920 resolution. | Missed | Passed |
The instructions your model reads when the skill loads.
Assemble a food-product sizzle ad from a config: a wordless macro-tabletop photorealistic sizzle for a physical food / CPG product — tactile tabletop photography in ONE look pack (setting + light chosen per brand; the demo's is a warm tungsten kitchen), ~4 dynamic macro scenes (hands tearing, a flat lay, a partial-face bite, a box / pack hero) flowing into a static end card, carried by a non-diegetic instrumental music bed + a few diegetic SFX with NO voiceover. This capability is the FREE, deterministic assembly — normalized concat, the anti-AI grain pass, the audio (music bed + SFX) composite, the PIL end card, and the optional serif stat-callout pills.
scripts/config.example.json is the worked example (Lineage Provisions "Beef Sticks Sizzle", ~14s
1080×1920 9:16, ~4 macro scenes + a static end card); scripts/PIPELINE.md maps every config block
to its source step and scripts/README.md documents the free assembly.
The recipe asks these before any paid step; this capability only assembles what they produced. The demo's value is an example, never a default:
setting — surface + room → look_pack.style_descriptor, scenes[].keyframe_prompt,
end_card.background. Demo: warm rustic kitchen (linen, wood, butcher paper, cast iron).light → look_pack.style_descriptor + palette_anchors. Demo: warm tungsten window light.hands — whose hands / mouth appear, or product-only → scenes[].keyframe_prompt +
motion_hint. Demo: a man's weathered hands, stubbled jaw.music → music.prompt. Demo: upbeat bluegrass (banjo, acoustic guitar, brush percussion).This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are separate
capabilities: ~4 photographic macro keyframes (create-image-fal, Nano Banana; the box / pack hero
grounds on the real product PNG); one locked-off, anti-shake i2v clip per keyframe (create-video-fal,
Seedance); and a non-diegetic instrumental bed in the music choice (create-music-elevenlabs). Given the ~4
clips + the music bed + the diegetic SFX + the real logo PNG + the real product PNG,
render-food-product-sizzle normalizes fps / SAR, concats the body clips, applies the anti-AI grain
pass, composites the audio (bed + SFX at their cue points), composites the static PIL end card, burns
the optional serif callout pills, and muxes → the master. Re-cuts reuse the existing keyframes /
clips / music and cost $0.
test cases passed, vs 9 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.