Install any skill in seconds. Free to start, no credit card required.
Get Started Free →VR/AR development principles. Comfort, interaction, performance requirements.
.claude/skills/davila7-vr-ar/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✓→✓ | = Same ✓ | 25% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 29% | 0% |
| case-06 | ✓→✓ | = Same ✓ | -44% | 0% |
| case-07 | ✓→✓ | = Same ✓ | -56% | 0% |
| case-08 | ✓→✓ | = Same ✓ | 62% | 0% |
> Immersive experience principles.
| Platform | Use Case | |----------|----------| | Quest | Standalone, wireless | | PCVR | High fidelity | | PSVR | Console market | | WebXR | Browser-based |
| Platform | Use Case | |----------|----------| | ARKit | iOS devices | | ARCore | Android devices | | WebXR | Browser AR | | HoloLens | Enterprise |
| Cause | Solution | |-------|----------| | Locomotion | Teleport, snap turn | | Low FPS | Maintain 90 FPS | | Camera shake | Avoid or minimize | | Rapid acceleration | Gradual movement |
| Platform | FPS | Resolution | |----------|-----|------------| | Quest 2 | 72-90 | 1832x1920 | | Quest 3 | 90-120 | 2064x2208 | | PCVR | 90 | 2160x2160+ | | PSVR2 | 90-120 | 2000x2040 |
| Type | Use | |------|-----| | Point + click | UI, distant objects | | Grab | Manipulation | | Gesture | Magic, special actions | | Physical | Throwing, swinging |
| Cue | Importance | |-----|------------| | Stereo | Primary depth | | Motion parallax | Secondary | | Shadows | Grounding | | Occlusion | Layering |
| ❌ Don't | ✅ Do | |----------|-------| | Move camera without player | Player controls camera | | Drop below 90 FPS | Maintain frame rate | | Use tiny UI text | Large, readable text | | Ignore arm length | Scale to player reach |
> Remember: Comfort is not optional. Sick players don't play.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 29,145 | 30,721 | +5% | 1 | 1 | 0% | 4,587 | 5,539 | +21% | 0 | 0 | — |
case-01 | fail→fail | 35,092 | 26,309 | -25% | 1 | 1 | 0% | 5,850 | 4,934 | -16% | 0 | 0 | — |
case-03 | pass→pass | 17,562 | 20,433 | +16% | 1 | 1 | 0% | 2,970 | 3,709 | +25% | 0 | 0 | — |
case-04 | fail→fail | 18,149 | 14,770 | -19% | 1 | 1 | 0% | 3,033 | 3,239 | +7% | 0 | 0 | — |
case-05 | pass→pass | 19,200 | 19,517 | +2% | 1 | 1 | 0% | 3,121 | 4,018 | +29% | 0 | 0 | — |
case-06 | pass→pass | 11,308 | 3,049 | -73% | 1 | 1 | 0% | 1,967 | 1,106 | -44% | 0 | 0 | — |
case-07 | pass→pass | 13,303 | 2,040 | -85% | 1 | 1 | 0% | 2,279 | 992 | -56% | 0 | 0 | — |
case-08 | pass→pass | 4,562 | 3,028 | -34% | 1 | 1 | 0% | 720 | 1,169 | +62% | 0 | 0 | — |
case-09 | pass→pass | 14,323 | 9,962 | -30% | 1 | 1 | 0% | 2,379 | 2,256 | -5% | 0 | 0 | — |
case-10 | pass→pass | 9,423 | 5,208 | -45% | 1 | 1 | 0% | 1,772 | 1,656 | -7% | 0 | 0 | — |
case-11 | pass→pass | 9,666 | 4,063 | -58% | 1 | 1 | 0% | 1,757 | 1,434 | -18% | 0 | 0 | — |
case-12 | pass→pass | 10,332 | 9,412 | -9% | 1 | 1 | 0% | 1,805 | 2,187 | +21% | 0 | 0 | — |
case-13 | pass→pass | 12,338 | 11,002 | -11% | 1 | 1 | 0% | 2,248 | 2,641 | +17% | 0 | 0 | — |
case-14 | pass→pass | 5,162 | 2,930 | -43% | 1 | 1 | 0% | 821 | 1,155 | +41% | 0 | 0 | — |
case-15 | pass→pass | 12,145 | 8,979 | -26% | 1 | 1 | 0% | 1,990 | 2,132 | +7% | 0 | 0 | — |
case-16 | pass→pass | 6,239 | 2,556 | -59% | 1 | 1 | 0% | 996 | 1,080 | +8% | 0 | 0 | — |
case-17 | pass→pass | 15,583 | 3,255 | -79% | 1 | 1 | 0% | 2,401 | 1,124 | -53% | 0 | 0 | — |
case-18 | pass→pass | 7,496 | 2,273 | -70% | 1 | 1 | 0% | 1,166 | 1,007 | -14% | 0 | 0 | — |
case-19 | pass→pass | 8,889 | 2,256 | -75% | 1 | 1 | 0% | 1,409 | 1,048 | -26% | 0 | 0 | — |
case-20 | pass→pass | 12,919 | 10,228 | -21% | 1 | 1 | 0% | 2,112 | 2,360 | +12% | 0 | 0 | — |
case-21 | pass→pass | 14,599 | 12,346 | -15% | 1 | 1 | 0% | 2,471 | 2,763 | +12% | 0 | 0 | — |
case-22 | pass→pass | 13,447 | 7,786 | -42% | 1 | 1 | 0% | 2,130 | 1,862 | -13% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.