Designing for visionOS — spatial layout and ergonomics (60pt eye targets, field-of-view placement, dynamic scale), eyes-and-hands input with hover rules, motion and visual comfort (the 0.2 Hz rule, vection, depth-cue agreement), immersion strategy, spatial sound, and the video-format decision guide.
SkillScore95Maintained
Automatic
◆Design & UX Review pack
Last verified 8/18/2026
What it changes
Passed 21 of 22 test cases with the skill, and 16 of 22 without it.
Without skill73%
With skill95%
Checks it passed that the model alone missed
Requires a 20pt overlap on the bottom edge
Requires visual state snap upon finger contact
Specifies an entry reveal delay around 0.8 seconds
and 2 more in the full report
5 fixed16 passed either way1 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+70%
Agent turns
0%
Response time
-32%
Model gemini-3.6-flashMeasured 8/18/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
A custom gaze hover reveal control in a visionOS window triggers immediately with a 0.0s entry delay and fades out over 1.5 seconds when gaze leaves. Evaluate these hover timing parameters.
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies an entry reveal delay around 0.8 seconds
Missed
Passed
Specifies an exit fade duration around 0.2 seconds
Passed
Passed
case-18 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md152 linessingle file
Spatial Design (visionOS)
The design rules that make a visionOS app comfortable instead of exhausting — distilled from
Apple's spatial-design sessions (WWDC23–26). Widget-specific rules live in visionos/widgets;
custom immersive-environment production and budgets live in immersive-environments.md.
When This Skill Activates
Designing or reviewing a visionOS app, window, volume, or immersive space
"Users say it's tiring / uncomfortable / hard to hit controls"
Porting an iPad app and deciding what should become spatial
Adding hover effects, custom gestures, environments, or spatial audio
Choosing a video experience format (spatial, 180°, 360°, wide-FOV, Apple Immersive)
The prime directive: find the key moment
Don't window a 2D app. Identify the one thing only possible on visionOS — the "key moment" —
and build around it. Immersion has three approaches, and full immersion is not mandatory:
full environments · integration with real surroundings (scene sensing) · meaningful audio.
Layout & ergonomics
Wide beats tall — layouts match the human field of view; turning the head left/right is
easier than up/down. Center = primary content; edges = secondary, infrequent actions.
Default placement sits along the natural line of sight, a bit further than arm's reach;
extended reading goes farther out, centered and slightly below eye line.
Design in points, not meters — dynamic scale keeps windows legible at any distance
(they scale up as they move away). Never fixed scale for UI; keep custom UI facing the viewer.
Depth is hierarchy, used sparingly — "prefer subtle depth" (a modal pushes its parent
back). Keep text flat; 3D text is hard to read at an angle.
Glass, never solid window backgrounds — solid colors block the world, don't adapt to
lighting, and "can feel constricting." Elements on glass use vibrancy + white text/symbols;
system colors over custom (they're calibrated for legibility). Brand color goes in
backgrounds or whole buttons, not glyphs.
Typography runs heavier than iOS: body = medium (vs regular), titles = bold (vs
semibold), slightly increased tracking. Avoid small/lightweight custom fonts.
Component specs: vertical tab bar fixed left, ≤6 items, expands on gaze · ornaments
overlap the window's bottom edge by 20pt, borderless buttons inside · sheets appear
centered at the parent's Z while the parent dims and pushes back · nested corners concentric
(outer radius = inner + padding).