capabilities

Render Model Comparison Grid

Render a 'model comparison grid' video from a config — a fal-style "same prompt, N contenders" showcase — a dark real-DOM stage where per beat a monospace prompt fades in centered, docks to a small top strip, then a labeled 2-4 panel grid (static images OR muted video clips, mixable per cell) staggers in and holds for comparison, plus a minimal end card — frame-stepped via Playwright (video cells are frame-seeked deterministically) and encoded with FFmpeg. Deterministic assembly, FREE (cell media comes from create-image-fal / create-video-fal, music from create-music-elevenlabs), text stays pixel-crisp. Use for the model-comparison-grid format.

by Athina AI

Run in Gooseworks View skill in Github

Install

Terminal

npx gooseworks install --all

# then, in Claude Code, Cursor, or Codex:
/gooseworks use the render-model-comparison-grid skill

About This Skill

render-model-comparison-grid

Render the 'model comparison grid' format from a config. The signature of this format is a "Same prompt. N models." gauntlet: a dark stage where, per beat, a PROMPT eyebrow + the (condensed) prompt fades in centered in monospace and holds readable ~0.8s, then docks to a small top strip while a grid of 2-4 labeled panels staggers in (0.15s apart) and holds for side-by-side comparison. A persistent model/variant label sits under each panel; column order is identical on every beat. Ends on a minimal end card (headline + column names only — no meta-stats line).

The grid is media-agnostic per cell: any cell is a static image or a muted video clip (i2v outputs, screen recordings), mixable within one beat. Video cells loop during the hold and are frame-seeked deterministically (the renderer awaits each seek), so the render never depends on wall-clock playback timing.

The renderer itself is FREE/deterministic (Playwright frame-step + FFmpeg). The paid inputs are separate capabilities: the cell images come from create-image-fal, the cell clips from create-video-fal, and the music bed from create-music-elevenlabs. Prompt text and labels are real DOM — never AI-rendered.

Default shape: 5 beats × 4.5s + 2.5s end card = 25.0s @ 1280×720/30fps, all configurable from one config.json.

Run

build_composition.py --config config.json --output hyperframe.html ; render_seekable_hyperframe.py hyperframe.html master-silent.mp4 <duration> --fps 30 --width 1280 --height 720 — dark stage, staggered grid, deterministic, $0. The config schema is documented at the top of scripts/build_composition.py; scripts/config.example.json IS the shipped worked example (re-point the cell paths at your own media).

build_composition.py validates every cell path and the column count (2-4), infers each cell's media type from its extension (.png/.jpg/.jpeg/.webp → image; .mp4/.mov/.webm/.m4v → muted video), and emits a self-contained HTML that exposes window.mediaReady() + window.renderAt(t). render_seekable_hyperframe.py awaits both, so <video> cells seek to the right frame before each screenshot — never a frozen first frame.

Contract

Deterministic + FREE (Playwright frame-step + FFmpeg); no paid calls in this capability.
Columns = panels-per-beat (2-4); every beat supplies exactly that many cells, same order.
The template recipe (DB) supplies the config; cell images/clips + music are separate capabilities.
State is computed entirely in renderAt(t) — never CSS animation-delay/transitions (Playwright scrubbing traps delayed animations in pre-state).
Video cells must decode in the render Chromium (H.264 yes, ProRes no — transcode .mov ProRes to H.264 first). An images-only grid has no decode dependency.

What's included

Deterministic + FREE (Playwright frame-step + FFmpeg); no paid calls in this capability.

Columns = panels-per-beat (2-4); every beat supplies exactly that many cells, same order.

The template recipe (DB) supplies the config; cell images/clips + music are separate

State is computed entirely in renderAt(t) — never CSS animation-delay/transitions

Video cells must decode in the render Chromium (H.264 yes, ProRes no — transcode .mov

Render Offer Ad

Render a punchy ~12s vertical (9:16) music-only direct-response OFFER ad as a 4-beat kinetic-typography film — HEADLINE slam → real PRODUCT drop → CLAIM/proof → CTA pill — from one config of copy slots, a real product photo, a brand palette, fonts, bpm, and beat split. DETERMINISTIC + FREE (a bundled Remotion project; springs + interpolate, no AI-gen for visuals). Backgrounds are engine gradient divs off the palette, props are inline SVG, the ONLY composited bitmap is the REAL product photo (objectFit:contain, never stretched), and ALL headline/claim/CTA/URL/wordmark text is typeset in the engine — never AI-rendered (the format's credibility guard). A driver binds the config to Remotion input props, renders the 9:16 master, and derives a 1:1 center-crop with ffmpeg. Two gating checks run before render (claim verbs must match the product's physical format; the claim beat needs an edge-entry mechanism prop). Use for the motion-graphics-offer-ad format.

Render Myth Vs Fact

Assemble a myth-vs-fact kinetic-typography explainer video ad (≈29.5s, 9:16) from N myth/fact pairs + hook / turn / punch copy + palette + a brand end-card PNG + a VO track — a hook, 3 red-strike MYTH cards that flip to teal-check FACT cards (per-line strikethrough that crosses EVERY wrapped line), a "what actually works" turn, an optional proof reveal, a punch line, and a static end card. DETERMINISTIC assembly with ZERO AI-gen visuals — HTML hyperframes rendered frame-exact via Playwright (`window.renderAt(t)`, animation a pure function of beat-local time), Whisper beat-snap to VO word onsets, concat at a uniform fps, karaoke `.ass` captions burned last (suppressed on the proof + end-card beats), and a VO + optional music mix (music −20 dB, `amix normalize=0`, tail fade). FREE (Python + Playwright + ffmpeg); the recipe supplies the copy / palette / end-card / VO and gates the paid VO / music / Whisper calls to their own capabilities. Use for the myth-vs-fact format.

Render Airdrop Carousel

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a ___ · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an Accept tap; a chime + soft per-swap ticks track the swaps. DETERMINISTIC assembly — an HTML card (real DOM text) rendered to PNG via headless Chrome, chroma-keyed, its magenta window refilled per-product in PIL, then animated + audio-synthed with FFmpeg. FREE (no paid model calls); the recipe supplies the brand line, product images, and payoff and gates the only optional paid step (a hero shot when the brand has NO usable photo → create-image-fal). Use for the airdrop-notification-carousel format.