Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
.claude/skills/nexu-io-minimalist-ui/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 56% | 0% |
Name: Premium Utilitarian Minimalism & Editorial UI Description: An advanced frontend engineering directive for generating highly refined, ultra-minimalist, "document-style" web interfaces analogous to top-tier workspace platforms. This protocol strictly enforces a high-contrast warm monochrome palette, bespoke typographic hierarchies, meticulous structural macro-whitespace, bento-grid layouts, and an ultra-flat component architecture with deliberate muted pastel accents. It actively rejects standard generic SaaS design trends.
The AI must strictly avoid the following generic web development defaults:
shadow-md, shadow-lg, shadow-xl). Shadows must be practically non-existent or heavily customized to be ultra-diffuse and low opacity (< 0.05).rounded-full (pill shapes) for large containers, cards, or primary buttons.The interface must rely on extreme typographic contrast and premium font selection to establish an editorial feel.
font-family: 'SF Pro Display', 'Geist Sans', 'Helvetica Neue', 'Switzer', sans-serif.font-family: 'Lyon Text', 'Newsreader', 'Playfair Display', 'Instrument Serif', serif. Apply tight tracking (letter-spacing: -0.02em to -0.04em) and tight line-height (1.1).font-family: 'Geist Mono', 'SF Mono', 'JetBrains Mono', monospace.#000000). Use off-black/charcoal (#111111 or #2F3437) with a generous line-height of 1.6 for legibility. Secondary text should be muted gray (#787774).Color is a scarce resource, utilized only for semantic meaning or subtle accents.
#FFFFFF or Warm Bone/Off-White #F7F6F3 / #FBFBFA.#FFFFFF or #F9F9F8.#EAEAEA or rgba(0,0,0,0.06).#FDEBEC (Text: #9F2F2D)#E1F3FE (Text: #1F6C9F)#EDF3EC (Text: #346538)#FBF3DB (Text: #956400)border: 1px solid #EAEAEA.8px or 12px maximum.24px to 40px).#111111, text #FFFFFF.4px to 6px). No box-shadow.#333333 or a micro-scale transform: scale(0.98).border-radius: 9999px), very small typography (text-xs), uppercase with wide tracking (letter-spacing: 0.05em).border-bottom: 1px solid #EAEAEA.+ and - icon for the toggle state.<kbd> tags: border: 1px solid #EAEAEA, border-radius: 4px, background: #F7F6F3, using the Monospace font.opacity: 0.04 warm grain) to blend photos into the monochrome palette. Never use oversaturated stock photos. Use reliable placeholders like https://picsum.photos/seed/{context}/1200/800 when real assets are unavailable.radial-gradient with warm tones at opacity: 0.03), or minimal geometric line patterns to add depth without breaking the clean aesthetic.Motion should feel invisible — present but never distracting. The goal is quiet sophistication, not spectacle.
translateY(12px) + opacity: 0 resolving over 600ms with cubic-bezier(0.16, 1, 0.3, 1). Use IntersectionObserver, never window.addEventListener('scroll').box-shadow transitioning from 0 0 0 to 0 2px 8px rgba(0,0,0,0.04) over 200ms). Buttons respond with scale(0.98) on :active.animation-delay: calc(var(--index) * 80ms)). Never mount everything at once.animation-duration: 20s+, opacity: 0.02-0.04) drifting behind hero sections. Must be applied to a position: fixed; pointer-events: none layer. Never on scrolling containers.transform and opacity. No layout-triggering properties (top, left, width, height). Use will-change: transform sparingly and only on actively animating elements.When tasked with writing frontend code (HTML, React, Tailwind, Vue) or designing a layout:
py-24 or py-32 in Tailwind).max-w-4xl or max-w-5xl.1px solid #EAEAEA rule.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 97,828 | 43,691 | -55% | 1 | 1 | 0% | 8,260 | 10,341 | +25% | 0 | 0 | — |
case-02 | fail→pass | 53,373 | 39,322 | -26% | 1 | 1 | 0% | 8,246 | 10,327 | +25% | 0 | 0 | — |
case-03 | fail→pass | 34,339 | 47,342 | +38% | 1 | 1 | 0% | 7,114 | 9,525 | +34% | 0 | 0 | — |
case-04 | pass→fail | 19,561 | 51,548 | +164% | 1 | 1 | 0% | 2,574 | 10,305 | +300% | 0 | 0 | — |
case-10 | fail→pass | 30,178 | 33,410 | +11% | 1 | 1 | 0% | 5,021 | 8,758 | +74% | 0 | 0 | — |
case-05 | pass→pass | 14,417 | 20,311 | +41% | 1 | 1 | 0% | 1,885 | 4,968 | +164% | 0 | 0 | — |
case-06 | pass→pass | 11,459 | 14,892 | +30% | 1 | 1 | 0% | 2,281 | 4,179 | +83% | 0 | 0 | — |
case-07 | fail→pass | 30,960 | 51,121 | +65% | 1 | 1 | 0% | 6,219 | 10,207 | +64% | 0 | 0 | — |
case-08 | fail→pass | 38,301 | 40,683 | +6% | 1 | 1 | 0% | 5,423 | 8,445 | +56% | 0 | 0 | — |
case-09 | fail→pass | 46,336 | 40,629 | -12% | 1 | 1 | 0% | 7,495 | 10,306 | +38% | 0 | 0 | — |
case-11 | fail→pass | 39,716 | 51,201 | +29% | 1 | 1 | 0% | 8,227 | 10,308 | +25% | 0 | 0 | — |
case-12 | fail→fail | 23,378 | 37,000 | +58% | 1 | 1 | 0% | 5,022 | 7,873 | +57% | 0 | 0 | — |
case-13 | fail→pass | 38,183 | 51,915 | +36% | 1 | 1 | 0% | 8,051 | 10,308 | +28% | 0 | 0 | — |
case-14 | fail→pass | 33,451 | 51,530 | +54% | 1 | 1 | 0% | 5,389 | 10,313 | +91% | 0 | 0 | — |
case-15 | pass→pass | 26,059 | 47,026 | +80% | 1 | 1 | 0% | 3,640 | 8,926 | +145% | 0 | 0 | — |
case-16 | fail→fail | 11,548 | 61,473 | +432% | 1 | 1 | 0% | 2,434 | 9,507 | +291% | 0 | 0 | — |
case-17 | fail→pass | 34,800 | 49,540 | +42% | 1 | 1 | 0% | 5,619 | 10,295 | +83% | 0 | 0 | — |
case-18 | fail→pass | 27,839 | 40,234 | +45% | 1 | 1 | 0% | 4,553 | 8,436 | +85% | 0 | 0 | — |
case-19 | fail→fail | 21,202 | 16,902 | -20% | 1 | 1 | 0% | 2,935 | 5,299 | +81% | 0 | 0 | — |
case-20 | pass→pass | 18,632 | 31,857 | +71% | 1 | 1 | 0% | 4,068 | 8,365 | +106% | 0 | 0 | — |
case-21 | fail→fail | 27,991 | 32,991 | +18% | 1 | 1 | 0% | 4,298 | 7,343 | +71% | 0 | 0 | — |
case-22 | fail→fail | 26,508 | 39,040 | +47% | 1 | 1 | 0% | 4,231 | 9,904 | +134% | 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 +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.