Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A real-time synthwave scene — a perspective floor grid scrolling toward a banded retro sun under a neon starfield, all from one fragment shader. No textures. Rendered as a single self-contained `index.html`. Use when the brief asks for "synthwave", "outrun", "retro 80s", "neon grid", "perspective grid", "vaporwave", or a retro-futuristic hero. Open Design serves this in powered-preview mode so the GPU stack actually runs.
.claude/skills/nexu-io-webgl-neon-grid/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 195% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 256% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 191% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 65% | 0% |
Produce a single self-contained index.html that renders a real-time synthwave scene full-screen — a perspective floor grid, a banded retro sun, and a starfield — with a clean typographic overlay on top.
OpenDesign detects getContext('webgl2') and renders this file in powered preview — a cross-origin-isolated iframe with allow-same-origin. The full GPU pipeline is available; you do not need to work around the opaque sandbox.
webgl-neon-grid/
├── SKILL.md ← you're reading this
└── example.html ← a working synthwave grid + sun shader (READ FIRST)Read example.html end to end. Note the shape: a horizon split; above the horizon a sky gradient, a circular sun cut by horizontal scanline bands, and hashed stars; below the horizon a perspective floor grid (z = k / depth, x = uv.x * z) that scrolls with time, its lines thinning and fading with distance. Everything is analytic — no raymarch needed.
Synthwave lives on its gradient:
index.htmlabs(fract(gv) - 0.5) and a distance-scaled line width so far lines don't alias.sin(y * f) cuts on its lower half.#63fe13.webgl2 is unavailable.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 55,951 | 48,824 | -13% | 1 | 1 | 0% | 8,253 | 8,895 | +8% | 0 | 0 | — |
case-02 | fail→fail | 54,382 | 54,292 | -0% | 1 | 1 | 0% | 8,260 | 8,902 | +8% | 0 | 0 | — |
case-03 | fail→fail | 43,745 | 41,871 | -4% | 1 | 1 | 0% | 8,249 | 8,891 | +8% | 0 | 0 | — |
case-04 | pass→fail | 33,155 | 41,494 | +25% | 1 | 1 | 0% | 5,363 | 8,875 | +65% | 0 | 0 | — |
case-05 | fail→pass | 13,951 | 49,519 | +255% | 1 | 1 | 0% | 3,012 | 8,880 | +195% | 0 | 0 | — |
case-06 | pass→fail | 24,168 | 50,735 | +110% | 1 | 1 | 0% | 3,435 | 8,872 | +158% | 0 | 0 | — |
case-07 | pass→pass | 26,387 | 49,330 | +87% | 1 | 1 | 0% | 5,392 | 8,857 | +64% | 0 | 0 | — |
case-08 | pass→pass | 23,089 | 17,558 | -24% | 1 | 1 | 0% | 3,364 | 3,449 | +3% | 0 | 0 | — |
case-09 | pass→pass | 23,284 | 33,393 | +43% | 1 | 1 | 0% | 4,222 | 7,345 | +74% | 0 | 0 | — |
case-10 | fail→pass | 16,680 | 35,881 | +115% | 1 | 1 | 0% | 2,249 | 7,997 | +256% | 0 | 0 | — |
case-11 | fail→pass | 17,775 | 39,619 | +123% | 1 | 1 | 0% | 3,046 | 8,861 | +191% | 0 | 0 | — |
case-12 | pass→fail | 36,199 | 55,762 | +54% | 1 | 1 | 0% | 7,720 | 8,879 | +15% | 0 | 0 | — |
case-13 | pass→pass | 13,968 | 13,981 | +0% | 1 | 1 | 0% | 2,044 | 2,877 | +41% | 0 | 0 | — |
case-14 | pass→pass | 27,544 | 19,140 | -31% | 1 | 1 | 0% | 4,106 | 3,819 | -7% | 0 | 0 | — |
case-15 | pass→pass | 13,523 | 15,632 | +16% | 1 | 1 | 0% | 2,487 | 3,348 | +35% | 0 | 0 | — |
case-16 | fail→pass | 28,597 | 71,950 | +152% | 1 | 1 | 0% | 5,830 | 8,879 | +52% | 0 | 0 | — |
case-17 | pass→pass | 14,560 | 13,068 | -10% | 1 | 1 | 0% | 2,402 | 2,990 | +24% | 0 | 0 | — |
case-18 | pass→fail | 17,226 | 56,052 | +225% | 1 | 1 | 0% | 3,123 | 8,849 | +183% | 0 | 0 | — |
case-19 | pass→pass | 17,922 | 17,605 | -2% | 1 | 1 | 0% | 3,205 | 3,698 | +15% | 0 | 0 | — |
case-20 | pass→pass | 20,799 | 46,905 | +126% | 1 | 1 | 0% | 3,349 | 8,865 | +165% | 0 | 0 | — |
case-21 | pass→pass | 22,788 | 42,625 | +87% | 1 | 1 | 0% | 4,663 | 8,850 | +90% | 0 | 0 | — |
case-22 | pass→pass | 32,436 | 40,950 | +26% | 1 | 1 | 0% | 6,641 | 8,855 | +33% | 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. 4 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.