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/lingxling-vr-ar/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-02 | ✓→✗ | ▼ Worse | -33% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 16% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 1% | 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.
This skill is applicable to execute the workflow or actions described in the overview.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,489 | 27,426 | +48% | 1 | 1 | 0% | 2,818 | 3,547 | +26% | 0 | 0 | — |
case-02 | pass→fail | 32,512 | 16,415 | -50% | 1 | 1 | 0% | 5,336 | 3,565 | -33% | 0 | 0 | — |
case-03 | fail→pass | 20,241 | 12,861 | -36% | 1 | 1 | 0% | 2,681 | 2,392 | -11% | 0 | 0 | — |
case-04 | pass→pass | 7,259 | 2,743 | -62% | 1 | 1 | 0% | 1,147 | 1,163 | +1% | 0 | 0 | — |
case-05 | pass→pass | 17,385 | 6,108 | -65% | 1 | 1 | 0% | 2,444 | 1,534 | -37% | 0 | 0 | — |
case-06 | pass→pass | 10,769 | 4,015 | -63% | 1 | 1 | 0% | 1,588 | 1,297 | -18% | 0 | 0 | — |
case-07 | pass→pass | 13,364 | 10,965 | -18% | 1 | 1 | 0% | 2,062 | 2,113 | +2% | 0 | 0 | — |
case-08 | pass→pass | 10,628 | 6,186 | -42% | 1 | 1 | 0% | 1,615 | 1,571 | -3% | 0 | 0 | — |
case-09 | pass→pass | 4,166 | 3,382 | -19% | 1 | 1 | 0% | 683 | 1,178 | +72% | 0 | 0 | — |
case-10 | fail→fail | 19,500 | 11,039 | -43% | 1 | 1 | 0% | 2,639 | 2,392 | -9% | 0 | 0 | — |
case-11 | pass→pass | 9,975 | 2,406 | -76% | 1 | 1 | 0% | 1,272 | 1,033 | -19% | 0 | 0 | — |
case-12 | pass→pass | 10,749 | 2,140 | -80% | 1 | 1 | 0% | 1,648 | 972 | -41% | 0 | 0 | — |
case-13 | pass→pass | 10,997 | 7,570 | -31% | 1 | 1 | 0% | 1,697 | 1,613 | -5% | 0 | 0 | — |
case-14 | pass→pass | 12,936 | 3,675 | -72% | 1 | 1 | 0% | 1,766 | 1,376 | -22% | 0 | 0 | — |
case-15 | pass→pass | 7,514 | 2,886 | -62% | 1 | 1 | 0% | 975 | 1,100 | +13% | 0 | 0 | — |
case-16 | pass→pass | 5,995 | 17,855 | +198% | 1 | 1 | 0% | 807 | 1,120 | +39% | 0 | 0 | — |
case-17 | fail→pass | 13,502 | 5,582 | -59% | 1 | 1 | 0% | 1,845 | 1,610 | -13% | 0 | 0 | — |
case-18 | pass→pass | 11,610 | 2,634 | -77% | 1 | 1 | 0% | 1,444 | 1,117 | -23% | 0 | 0 | — |
case-19 | pass→pass | 9,601 | 2,507 | -74% | 1 | 1 | 0% | 1,345 | 1,138 | -15% | 0 | 0 | — |
case-20 | pass→fail | 24,359 | 24,965 | +2% | 1 | 1 | 0% | 3,597 | 4,169 | +16% | 0 | 0 | — |
case-21 | pass→pass | 16,093 | 17,067 | +6% | 1 | 1 | 0% | 3,287 | 4,084 | +24% | 0 | 0 | — |
case-22 | pass→pass | 24,392 | 19,154 | -21% | 1 | 1 | 0% | 3,333 | 4,340 | +30% | 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. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.