Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Minimal / clean / Linear / Notion / Vercel / whitespace-heavy UIs. Locked knobs: CRAFT=8, MOTION=3, DENSITY=2. Monochrome + one accent, Inter/Geist, hairline borders over shadows. Trigger on: minimal, clean, Linear-like, Notion-like, Vercel-like, whitespace-heavy.
.claude/skills/educlopez-ui-craft-minimal/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 108% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 122% | 0% |
<!-- HARNESS MIRROR — do not edit here. Canonical source: skills/ or commands/. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. -->
Pre-committed minimal style: editorial clean, Linear / Notion / Vercel. Whitespace is the composition. One accent, hairline borders, almost no motion.
Do not re-ask these in Discovery. Skip straight to accent + font confirmation if ambiguous.
1px solid oklch(92% 0.005 250) in place of shadows.All rules in ../ui-craft/SKILL.md apply. This file overrides knob defaults and adds style-specific guidance below. The anti-slop and craft tests still apply in full.
Typography
system-ui, -apple-system as fallback stack.tracking-tight / -0.02em above 24px, 500 or 600 max.text-wrap: balance on headings, text-wrap: pretty on paragraphs.Color
oklch(99% 0 0) (light) / oklch(14% 0.005 250) (dark).oklch(18% 0.01 250) primary, oklch(46% 0.01 250) secondary.oklch(92% 0.005 250) light / oklch(24% 0.008 250) dark. No colored borders.Spacing & layout
py-24 md:py-32 lg:py-40 (96 / 128 / 160px) minimum; 200px for hero on large screens.max-w-5xl typical; max-w-3xl for reading content.Borders & elevation
Motion
prefers-reduced-motion.Composition
Keep the reading list tight. Load only these from ../ui-craft/references/:
layout.md — spacing, hierarchy, compositiontypography.md — scale, readability, weightcolor.md — monochrome scales, OKLCH, dark modeaccessibility.md — focus, contrast, keyboardSkip dashboard.md, stack.md, sound.md unless explicitly relevant.
ui-craft-dense-dashboard.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→fail | 28,505 | 31,893 | +12% | 1 | 1 | 0% | 6,016 | 8,370 | +39% | 0 | 0 | — |
case-10 | fail→fail | 15,128 | 18,619 | +23% | 1 | 1 | 0% | 3,197 | 5,157 | +61% | 0 | 0 | — |
case-02 | fail→fail | 33,949 | 39,507 | +16% | 1 | 1 | 0% | 7,062 | 9,533 | +35% | 0 | 0 | — |
case-01 | fail→pass | 38,181 | 24,833 | -35% | 1 | 1 | 0% | 7,815 | 6,235 | -20% | 0 | 0 | — |
case-03 | fail→fail | 26,579 | 35,532 | +34% | 1 | 1 | 0% | 5,448 | 8,406 | +54% | 0 | 0 | — |
case-04 | pass→pass | 37,917 | 38,244 | +1% | 1 | 1 | 0% | 8,234 | 9,529 | +16% | 0 | 0 | — |
case-05 | pass→pass | 23,300 | 38,347 | +65% | 1 | 1 | 0% | 4,954 | 9,506 | +92% | 0 | 0 | — |
case-06 | pass→pass | 18,638 | 38,415 | +106% | 1 | 1 | 0% | 4,135 | 9,507 | +130% | 0 | 0 | — |
case-07 | fail→pass | 17,366 | 19,274 | +11% | 1 | 1 | 0% | 3,517 | 5,006 | +42% | 0 | 0 | — |
case-08 | fail→pass | 17,596 | 28,486 | +62% | 1 | 1 | 0% | 3,374 | 7,033 | +108% | 0 | 0 | — |
case-11 | fail→pass | 27,803 | 20,616 | -26% | 1 | 1 | 0% | 6,379 | 5,697 | -11% | 0 | 0 | — |
case-12 | pass→pass | 36,176 | 37,222 | +3% | 1 | 1 | 0% | 7,824 | 9,230 | +18% | 0 | 0 | — |
case-13 | fail→fail | 16,367 | 36,958 | +126% | 1 | 1 | 0% | 3,490 | 7,795 | +123% | 0 | 0 | — |
case-14 | fail→fail | 22,182 | 32,397 | +46% | 1 | 1 | 0% | 4,750 | 8,558 | +80% | 0 | 0 | — |
case-15 | fail→fail | 15,867 | 19,464 | +23% | 1 | 1 | 0% | 3,293 | 5,248 | +59% | 0 | 0 | — |
case-16 | fail→pass | 12,461 | 18,917 | +52% | 1 | 1 | 0% | 2,386 | 5,295 | +122% | 0 | 0 | — |
case-17 | fail→pass | 15,768 | 19,769 | +25% | 1 | 1 | 0% | 3,325 | 5,234 | +57% | 0 | 0 | — |
case-18 | fail→fail | 30,168 | 21,862 | -28% | 1 | 1 | 0% | 6,977 | 6,132 | -12% | 0 | 0 | — |
case-19 | fail→pass | 22,890 | 20,593 | -10% | 1 | 1 | 0% | 4,871 | 5,596 | +15% | 0 | 0 | — |
case-20 | fail→fail | 17,945 | 32,492 | +81% | 1 | 1 | 0% | 3,774 | 8,151 | +116% | 0 | 0 | — |
case-21 | fail→pass | 24,799 | 31,117 | +25% | 1 | 1 | 0% | 5,410 | 8,197 | +52% | 0 | 0 | — |
case-22 | pass→pass | 9,984 | 15,062 | +51% | 1 | 1 | 0% | 2,008 | 4,255 | +112% | 0 | 0 | — |
case-23 | fail→fail | 21,971 | 39,646 | +80% | 1 | 1 | 0% | 4,609 | 9,351 | +103% | 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. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 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.