Skip to main content
The skills map natural-language adjectives to specific framework settings. Using the right word gets you the right result without specifying technical details.

Motion & easing

Describe how motion should feel and the agent picks the matching GSAP ease:
Say thisAgent usesFeels like
smoothpower2.outNatural deceleration
snappypower4.outQuick and decisive
bouncyback.outOvershoots then settles
springyelastic.outOscillates into place
dramaticexpo.outFast start, long glide
dreamysine.inOutSlow, symmetrical
Timing shorthand: fast (0.2s) = energy, medium (0.4s) = professional, slow (0.6s) = luxury, very slow (1–2s) = cinematic. Each word, rendered — the same move, only the ease changes:
smooth · power2.out
snappy · power4.out
bouncy · back.out
springy · elastic.out
dramatic · expo.out
dreamy · sine.inOut

Camera language

Compositions have no physical camera, but camera words translate directly into scene transforms (or real camera moves in Three.js scenes):
Say thisAgent builds
slow push-in4–8% scale increase across the scene, gentle ease
pull back / widenscale decrease, often paired with elements entering
pan acrosshorizontal translate of the scene layer
drone orbitcontinuous camera orbit (Three.js scenes)
crane down/upvertical camera drift combined with a look-at shift
whip tofast blurred slide into the next framing
parallaxlayers translating at different rates for depth
The same scene under each camera word:
slow push-in
pull back
pan across
crane down
whip to
parallax
drone orbit (Three.js)

Depth language

Say thisAgent builds
near-lens / foreground bokehlarge, heavily-blurred elements drifting close to camera
depth planes2–3 layers moving at different speeds
out-of-focus backgroundblurred, slower-moving back layer
shallow depth of fieldsharp subject, blurred everything-else

Pacing language

Say thisAgent builds
punchy cuts1.5–4s per idea, hard cuts, overlapping entrances
cinematic holdslonger beats with ambient idle motion
beat-syncedcuts and accents on the music’s beat grid
breathing rooma held moment before the next beat starts
ambient idle1–2% breathing scale + slow drift during holds

Caption tones

Describe the energy of your captions and the agent picks matching typography, size, and animation:
ToneTypographyAnimationSize range
HypeHeavy weight fontsScale-pop72–96px
CorporateClean sans-serifFade + slide56–72px
TutorialMonospaceTypewriter48–64px
StorytellingSerifSlow fade44–56px
SocialRounded, playfulBounce56–80px
"Hype-style captions with scale-pop"
"Calm, elegant subtitles with slow fades"
"Karaoke-style word highlighting"
Per-word styling also works:
"Make brand names larger with accent color"
"Add bounce to emotional keywords"
"Highlight numbers differently"

Transitions

Every multi-scene composition benefits from transitions. Describe the energy level:
EnergyCSS optionShader option
CalmBlur crossfadeCross-warp morph
MediumPush slideWhip pan
HighZoom throughGlitch, ridged burn
Or describe by mood:
"Warm transitions for this wellness brand"
"Cold, clinical transitions for tech"
"Playful bouncy transitions"
"Dramatic zoom for the reveal"

Audio-reactive animation

Map audio frequency bands to visual properties. The agent uses these defaults:
Audio bandMaps toVisual effect
BassscalePulse on the beat
TrebleglowShimmer intensity
AmplitudeopacityBreathing
MidsshapeMorphing
"Make the text pulse with the beat"
"Add bass-driven scale to the logo"
"Create glow that responds to treble"
Keep audio-reactive effects subtle for text (3–6% intensity). Go bigger for backgrounds (10–30%).

Marker highlights

Hand-drawn emphasis effects for text:
ModeEffectBest for
highlightMarker sweepKey phrases
circleHand-drawn ellipseSingle words
burstRadiating linesHype moments
scribbleChaotic scratchCrossing out
sketchoutRectangle outlineCallouts
"Add a marker highlight sweep on 'revolutionary'"
"Circle this keyword with hand-drawn effect"
"Add burst lines around 'AMAZING'"
The five modes on the same sentence:
highlight
circle
burst
scribble
sketchout

Text-to-speech voices

TTS runs locally via Kokoro (no API key needed). Describe the content and the agent picks a voice, or request one directly:
Content typeRecommended voices
Product demoaf_heart, af_nova
Tutorialam_adam, bf_emma
Marketingaf_sky, am_michael
"Generate narration for this script"
"Create voiceover with a professional female voice"
"Add TTS with British male voice at 1.1x speed"

Rendering quality

QualityUse for
draftFast iteration
standardReview and feedback
highFinal delivery
"Quick draft render"
"Render at high quality"
"Export as transparent WebM"