Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained `index.html`. Use when the brief asks for "liquid metal", "molten chrome", "iridescent", "holographic", "metallic", "thin-film", or a reflective flowing surface. Open Design serves this in powered-preview mode so the GPU stack actually runs.
.claude/skills/nexu-io-webgl-liquid-metal/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -12% | 0% |
Produce a single self-contained index.html that renders a real-time metallic surface full-screen — molten chrome with an iridescent sheen — 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-liquid-metal/
├── SKILL.md ← you're reading this
└── example.html ← a working domain-warped chrome shader (READ FIRST)Read example.html end to end. Note the shape: a domain-warped fbm height field; a surface normal reconstructed from that field's gradient (finite differences); metallic shading = diffuse chrome ramp + a sharp specular (pow(dot(n,h), 80)) + a fresnel term; and an iridescent cosine palette (0.5 + 0.5*cos(2π(x + phase))) driven by height and fresnel for the thin-film sheen.
index.htmle ≈ 0.0016); a sharp specular exponent (≥ 60) is what reads as "metal".#63fe13 as the brand accent.webgl2 is unavailable.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→fail | 13,072 | 38,078 | +191% | 1 | 1 | 0% | 2,138 | 8,874 | +315% | 0 | 0 | — |
case-01 | fail→fail | 41,768 | 51,496 | +23% | 1 | 1 | 0% | 8,255 | 8,905 | +8% | 0 | 0 | — |
case-02 | fail→fail | 40,695 | 38,826 | -5% | 1 | 1 | 0% | 8,244 | 8,894 | +8% | 0 | 0 | — |
case-03 | fail→fail | 41,711 | 40,848 | -2% | 1 | 1 | 0% | 8,248 | 8,898 | +8% | 0 | 0 | — |
case-04 | fail→pass | 15,480 | 17,408 | +12% | 1 | 1 | 0% | 2,502 | 3,519 | +41% | 0 | 0 | — |
case-05 | pass→pass | 12,409 | 39,306 | +217% | 1 | 1 | 0% | 2,107 | 8,895 | +322% | 0 | 0 | — |
case-06 | pass→pass | 18,447 | 10,157 | -45% | 1 | 1 | 0% | 3,518 | 2,534 | -28% | 0 | 0 | — |
case-07 | pass→fail | 7,799 | 6,413 | -18% | 1 | 1 | 0% | 1,325 | 1,696 | +28% | 0 | 0 | — |
case-09 | fail→pass | 12,649 | 7,221 | -43% | 1 | 1 | 0% | 1,886 | 1,884 | -0% | 0 | 0 | — |
case-10 | fail→pass | 17,359 | 14,925 | -14% | 1 | 1 | 0% | 2,811 | 3,094 | +10% | 0 | 0 | — |
case-11 | fail→pass | 15,073 | 14,357 | -5% | 1 | 1 | 0% | 2,310 | 3,122 | +35% | 0 | 0 | — |
case-12 | pass→pass | 21,745 | 20,072 | -8% | 1 | 1 | 0% | 3,859 | 4,104 | +6% | 0 | 0 | — |
case-17 | pass→pass | 16,145 | 10,983 | -32% | 1 | 1 | 0% | 2,584 | 2,678 | +4% | 0 | 0 | — |
case-13 | pass→pass | 11,679 | 10,818 | -7% | 1 | 1 | 0% | 2,114 | 2,485 | +18% | 0 | 0 | — |
case-14 | pass→pass | 14,607 | 33,385 | +129% | 1 | 1 | 0% | 2,284 | 7,373 | +223% | 0 | 0 | — |
case-15 | fail→pass | 17,114 | 9,942 | -42% | 1 | 1 | 0% | 2,521 | 2,224 | -12% | 0 | 0 | — |
case-16 | fail→pass | 10,146 | 3,686 | -64% | 1 | 1 | 0% | 1,481 | 1,200 | -19% | 0 | 0 | — |
case-18 | pass→fail | 21,443 | 40,357 | +88% | 1 | 1 | 0% | 3,441 | 8,863 | +158% | 0 | 0 | — |
case-19 | pass→fail | 20,269 | 40,250 | +99% | 1 | 1 | 0% | 3,957 | 8,917 | +125% | 0 | 0 | — |
case-20 | pass→pass | 17,536 | 40,046 | +128% | 1 | 1 | 0% | 3,692 | 8,895 | +141% | 0 | 0 | — |
case-21 | pass→fail | 21,870 | 41,857 | +91% | 1 | 1 | 0% | 4,446 | 8,888 | +100% | 0 | 0 | — |
case-22 | pass→fail | 12,480 | 42,405 | +240% | 1 | 1 | 0% | 2,530 | 8,881 | +251% | 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. 6 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.