Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Editorial-minimalist web prototype. Warm monochrome canvas, serif display + grotesque body, 1px hairline borders, muted pastel chips, generous macro-whitespace, ambient micro-motion. Distilled from Leonxlnx/taste-skill `minimalist-skill`.
.claude/skills/nexu-io-web-prototype-taste-editorial/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 18% | 0% |
A single-page web prototype shaped like a Notion/Linear marketing site or premium documentation surface. Use when the brief asks for "clean", "editorial", "premium SaaS", "documentation", or "knowledge product".
Distilled from Leonxlnx/taste-skill — skills/minimalist-skill/SKILL.md and the spatial-rhythm rules in skills/taste-skill/SKILL.md. See example.html in this directory for a fully-realized template.
#FBFBFA or #F7F6F3), never pure white.#111111, secondary text #787774. Never #000000.1px solid #EAEAEA only. No drop shadows above 0 1px 2px rgba(0,0,0,0.04).letter-spacing: -0.025em, line-height: 1.05.#FDEBEC, #E1F3FE, #EDF3EC, #FBF3DB) for tags/badges. Never as section backgrounds.border-radius: 8–12px max. No pill containers, no rounded-full on cards.py-24 minimum, py-32 for hero.shadow-sm. No glows.#000000.backdrop-blur-md, hairline border).max-w-[52ch].1px dividers — never 3 equal cards.border-t only, no card.translateY(12px) → 0 + opacity 0 → 1 over 600ms cubic-bezier(0.16, 1, 0.3, 1). IntersectionObserver only.box-shadow from 0 0 0 to 0 2px 8px rgba(0,0,0,0.04) over 200ms.--index * 80ms.transform and opacity.1px solid #EAEAEApy-24| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 41,632 | 80,043 | +92% | 1 | 1 | 0% | 8,281 | 9,222 | +11% | 0 | 0 | — |
case-02 | fail→fail | 52,116 | 54,186 | +4% | 1 | 1 | 0% | 8,295 | 9,236 | +11% | 0 | 0 | — |
case-03 | fail→fail | 52,922 | 42,095 | -20% | 1 | 1 | 0% | 8,282 | 9,223 | +11% | 0 | 0 | — |
case-04 | fail→fail | 36,991 | 51,315 | +39% | 1 | 1 | 0% | 8,232 | 9,173 | +11% | 0 | 0 | — |
case-05 | pass→pass | 28,100 | 18,666 | -34% | 1 | 1 | 0% | 4,406 | 4,877 | +11% | 0 | 0 | — |
case-06 | pass→pass | 64,806 | 38,478 | -41% | 1 | 1 | 0% | 8,084 | 9,167 | +13% | 0 | 0 | — |
case-07 | fail→pass | 38,690 | 53,700 | +39% | 1 | 1 | 0% | 6,449 | 6,943 | +8% | 0 | 0 | — |
case-08 | fail→pass | 19,389 | 18,963 | -2% | 1 | 1 | 0% | 3,591 | 4,789 | +33% | 0 | 0 | — |
case-09 | fail→fail | 31,085 | 45,938 | +48% | 1 | 1 | 0% | 6,193 | 8,101 | +31% | 0 | 0 | — |
case-10 | fail→fail | 38,548 | 45,346 | +18% | 1 | 1 | 0% | 8,235 | 8,531 | +4% | 0 | 0 | — |
case-11 | fail→pass | 27,480 | 22,970 | -16% | 1 | 1 | 0% | 4,577 | 5,680 | +24% | 0 | 0 | — |
case-12 | fail→pass | 36,406 | 59,502 | +63% | 1 | 1 | 0% | 7,798 | 9,181 | +18% | 0 | 0 | — |
case-13 | pass→pass | 15,615 | 25,404 | +63% | 1 | 1 | 0% | 2,864 | 4,938 | +72% | 0 | 0 | — |
case-14 | fail→pass | 16,565 | 27,343 | +65% | 1 | 1 | 0% | 2,508 | 5,273 | +110% | 0 | 0 | — |
case-15 | fail→pass | 11,812 | 12,104 | +2% | 1 | 1 | 0% | 1,669 | 2,685 | +61% | 0 | 0 | — |
case-16 | fail→fail | 28,761 | 32,140 | +12% | 1 | 1 | 0% | 6,135 | 6,136 | +0% | 0 | 0 | — |
case-17 | pass→pass | 8,941 | 10,940 | +22% | 1 | 1 | 0% | 1,274 | 2,441 | +92% | 0 | 0 | — |
case-18 | fail→fail | 25,742 | 35,914 | +40% | 1 | 1 | 0% | 5,768 | 8,295 | +44% | 0 | 0 | — |
case-19 | fail→pass | 31,080 | 44,976 | +45% | 1 | 1 | 0% | 4,971 | 8,389 | +69% | 0 | 0 | — |
case-20 | fail→pass | 48,384 | 20,637 | -57% | 1 | 1 | 0% | 8,226 | 3,869 | -53% | 0 | 0 | — |
case-21 | fail→pass | 9,033 | 9,994 | +11% | 1 | 1 | 0% | 1,513 | 2,925 | +93% | 0 | 0 | — |
case-22 | fail→pass | 34,427 | 19,575 | -43% | 1 | 1 | 0% | 5,808 | 5,167 | -11% | 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 +50 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.