Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gooseworks-ai/render-glassy-matte-grwm
Assemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 products step by step while a SEPARATE ElevenLabs voiceover narrates and every scene cut is snapped to the VO's product-name word-starts (Whisper word-level timestamps), then ~5 Playwright product overlay cards (real PDP-verified taglines) are composited onto the master each on its product-NAME word-start, the SEPARATE VO is mixed on top of a ducked music bed at loudnorm I=-14, clean-white 3-words/cue
Passed 19 of 22 test cases with the skill, and 5 of 22 without it.
and 19 more in the full report
14 fixed5 passed either way3 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 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
At the conclusion of the GRWM video routine, what image asset should be appended as the final video scene, and how long should it hold?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies appending a flat-lay still image at the end of the video. | Missed | Passed |
| Specifies a hold duration of approximately 4 seconds for the end card. | Missed | Passed |
The instructions your model reads when the skill loads.
Assemble a multi-scene GRWM beauty-demo ad from a config — a locked-identity creator applies ~5 makeup/skincare products step by step in a chosen setting, a separate ElevenLabs voiceover narrates the routine, and every scene cut is snapped to the VO's product-name word-starts, with ~5 Playwright product overlay cards on the product-name beats, a ducked music bed, burned captions, and a flat-lay end card. This capability is the FREE, deterministic assembly — the Whisper-driven re-cut + hard-concat, the Playwright card render + card composite, the VO + music mix, the caption burn, and the flat-lay end card.
This is the multi-scene beauty demo, distinct from the single-take apparel outfit-reveal
(ugc-grwm, one Seedance reference-to-video call with native lip-sync and minimal post). Here the
timeline is driven by a SEPARATE VO and the scenes are re-cut to its word-starts.
scripts/config.example.json is the worked example (DIBS Beauty "5-Step Glassy Matte Routine",
~32s 1080×1920 9:16, 12 VO-snapped cuts + 5 product cards); scripts/PIPELINE.md maps every
config block to its source step and scripts/README.md documents the free assembly.
The creative calls come from the recipe's choices, asked of the user before any paid step. The
demo's picks are examples, never defaults. This capability only assembles what those choices
produced; it hardcodes none of them.
assets.creator_anchor, the look in the scene beats). The
demo used a young woman.vo.voice_id / vo.voice_name). The demo used ElevenLabs Karri.assets.vanity_world). The demo used a sage-green vanity.vo.script, vo.style). The demo was upbeat and friendly.music.prompt; "none" = VO only, skip the music mix). The demo
used a warm acoustic bed.Card colours come from palette (the brand kit), not the demo's cream + pink.
This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
separate capabilities — the SEPARATE narration VO (create-music-elevenlabs, or a user-supplied
mp3; word-level Whisper timestamps set the timeline), ~7 Seedance scene clips one per product step
(create-video-fal), the ~5 white-bg product cutouts + the flat-lay end-card still
test cases passed, vs 5 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.