Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Dense dashboard / admin / Bloomberg / Retool / data-heavy internal tools. Locked knobs: CRAFT=7, MOTION=3, DENSITY=9. IBM Plex + mono numbers, semantic palette, 4/8px grid, sparklines, tabular-nums. Trigger on: dashboard, admin panel, data-dense, analytics, Bloomberg-like, Retool-like.
.claude/skills/educlopez-ui-craft-dense-dashboard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 111% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 123% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 19% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 19% | 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 dense style: data-first, keyboard-first, operator tools. Bloomberg, Retool, Linear issues view, admin panels. Every pixel earns its place.
Do not re-ask these in Discovery. Confirm brand accent + dark/light preference only.
tabular-nums on every numeric column; mono on identifiers.px-3 py-2 table cells, gap-2 toolbars.⌘K, J/K, E to edit).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
tabular-nums on every numeric column, metric card, timestamp, duration.font-variant-numeric: tabular-nums slashed-zero for IDs + codes.Color (semantic palette required)
oklch(60% 0.12 150)oklch(72% 0.13 75)oklch(58% 0.15 25)oklch(62% 0.12 240)Spacing & layout
px-3 py-2 default; px-2 py-1.5 for ultra-dense.gap-2, h-9 controls, text-sm.p-4, 8px radius; 1px border over shadow.Data display
tabular-nums + right-aligned.+12.5% in semantic color, no pill.Chrome & navigation
×, no pill fill.⌘K visible in header search affordance.Page 3 of 42 + tabular-nums, plus J/K navigation.Motion
oklch(96% 0.002 250) light / oklch(20% 0.005 250) dark, 80ms.Load these from ../ui-craft/references/:
dashboard.md — primary reference; metric cards, charts, sidebar, tablestypography.md — tabular-nums, mono pairing, scalemotion.md Rendering Performance — compositor pipeline, layer promotion, scroll-linked motionresponsive.md — tablet + laptop breakpoints, toolbar collapseSkip inspiration.md (landing-page focused), sound.md.
tabular-nums.⌘K, row shortcuts, help trigger.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 17,715 | 47,877 | +170% | 1 | 1 | 0% | 3,696 | 9,753 | +164% | 0 | 0 | — |
case-01 | fail→fail | 40,148 | 40,745 | +1% | 1 | 1 | 0% | 8,245 | 9,780 | +19% | 0 | 0 | — |
case-02 | fail→fail | 38,989 | 38,801 | -0% | 1 | 1 | 0% | 8,252 | 9,787 | +19% | 0 | 0 | — |
case-03 | fail→fail | 39,053 | 41,556 | +6% | 1 | 1 | 0% | 8,245 | 9,780 | +19% | 0 | 0 | — |
case-04 | pass→pass | 25,650 | 36,824 | +44% | 1 | 1 | 0% | 5,212 | 9,632 | +85% | 0 | 0 | — |
case-05 | fail→pass | 17,111 | 26,724 | +56% | 1 | 1 | 0% | 3,358 | 7,072 | +111% | 0 | 0 | — |
case-06 | pass→pass | 16,466 | 38,608 | +134% | 1 | 1 | 0% | 3,006 | 9,757 | +225% | 0 | 0 | — |
case-07 | fail→pass | 20,232 | 37,508 | +85% | 1 | 1 | 0% | 4,372 | 9,761 | +123% | 0 | 0 | — |
case-08 | fail→fail | 20,966 | 36,814 | +76% | 1 | 1 | 0% | 4,808 | 9,669 | +101% | 0 | 0 | — |
case-09 | fail→fail | 29,289 | 38,048 | +30% | 1 | 1 | 0% | 6,598 | 9,760 | +48% | 0 | 0 | — |
case-10 | pass→pass | 17,713 | 37,050 | +109% | 1 | 1 | 0% | 3,697 | 9,758 | +164% | 0 | 0 | — |
case-11 | fail→pass | 12,540 | 15,956 | +27% | 1 | 1 | 0% | 2,561 | 4,766 | +86% | 0 | 0 | — |
case-13 | fail→fail | 17,805 | 36,362 | +104% | 1 | 1 | 0% | 3,949 | 9,758 | +147% | 0 | 0 | — |
case-14 | pass→pass | 23,649 | 36,230 | +53% | 1 | 1 | 0% | 4,987 | 9,757 | +96% | 0 | 0 | — |
case-15 | pass→pass | 15,126 | 32,399 | +114% | 1 | 1 | 0% | 2,961 | 8,310 | +181% | 0 | 0 | — |
case-16 | pass→pass | 15,009 | 35,894 | +139% | 1 | 1 | 0% | 2,947 | 9,323 | +216% | 0 | 0 | — |
case-17 | pass→pass | 18,196 | 35,225 | +94% | 1 | 1 | 0% | 3,530 | 8,917 | +153% | 0 | 0 | — |
case-18 | pass→pass | 16,691 | 28,830 | +73% | 1 | 1 | 0% | 3,302 | 7,633 | +131% | 0 | 0 | — |
case-19 | pass→pass | 17,263 | 25,195 | +46% | 1 | 1 | 0% | 3,447 | 6,469 | +88% | 0 | 0 | — |
case-20 | pass→fail | 39,357 | 42,914 | +9% | 1 | 1 | 0% | 8,231 | 9,766 | +19% | 0 | 0 | — |
case-21 | pass→pass | 20,061 | 40,071 | +100% | 1 | 1 | 0% | 4,197 | 9,754 | +132% | 0 | 0 | — |
case-22 | pass→fail | 37,581 | 42,818 | +14% | 1 | 1 | 0% | 8,228 | 9,763 | +19% | 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 -14 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.