Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create minimal framed grid layouts with thin visible boundary lines, L-shaped corner brackets, subtle diagonal line texture, and strict section alignment. Use when asked for clean, neutral, precise, structured, editorial, technical, or guide-border web layouts.
.claude/skills/mengto-framed-grid-layout/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 21% | 0% |
1px borders, low-contrast dividers, and subtle bracket marks.Use neutral colors and tune contrast per theme.
css:root { --fg-bg: #f7f7f4; --fg-surface: rgba(255, 255, 255, 0.62); --fg-line: rgba(24, 24, 27, 0.14); --fg-line-strong: rgba(24, 24, 27, 0.34); --fg-texture: rgba(24, 24, 27, 0.035); --fg-gap: 16px; --fg-pad: clamp(16px, 2vw, 28px); --fg-corner: 18px; }
Use the parent grid to enforce vertical and horizontal alignment.
css.framed-grid { min-height: 100vh; padding: var(--fg-gap); background: repeating-linear-gradient( 135deg, transparent 0 11px, var(--fg-texture) 11px 12px ), var(--fg-bg); display: grid; grid-template-columns: repeat(12, minmax(0, 1fr)); gap: var(--fg-gap); } .framed-grid > * { min-width: 0; }
Each section gets the same box model, line weight, and padding.
css.frame { position: relative; border: 1px solid var(--fg-line); background: var(--fg-surface); padding: var(--fg-pad); overflow: hidden; } .frame + .frame { margin-top: 0; }
Use background layers so brackets stay crisp without extra markup.
css.frame-brackets { background: linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) left top / var(--fg-corner) 1px no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) left top / 1px var(--fg-corner) no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) right top / var(--fg-corner) 1px no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) right top / 1px var(--fg-corner) no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) left bottom / var(--fg-corner) 1px no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) left bottom / 1px var(--fg-corner) no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) right bottom / var(--fg-corner) 1px no-repeat, linear-gradient(var(--fg-line-strong), var(--fg-line-strong)) right bottom / 1px var(--fg-corner) no-repeat, var(--fg-surface); }
Prefer explicit grid spans over ad hoc widths.
css.span-12 { grid-column: span 12; } .span-8 { grid-column: span 8; } .span-6 { grid-column: span 6; } .span-4 { grid-column: span 4; } @media (max-width: 760px) { .framed-grid { grid-template-columns: 1fr; } .span-12, .span-8, .span-6, .span-4 { grid-column: 1 / -1; } }
html<main class="framed-grid"> <section class="frame frame-brackets span-12">...</section> <section class="frame frame-brackets span-8">...</section> <aside class="frame frame-brackets span-4">...</aside> <section class="frame frame-brackets span-6">...</section> <section class="frame frame-brackets span-6">...</section> </main>
0.05 opacity.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | 20,162 | 10,797 | -46% | 1 | 1 | 0% | 4,194 | 3,528 | -16% | 0 | 0 | — |
case-06 | fail→fail | 17,284 | 11,066 | -36% | 1 | 1 | 0% | 3,498 | 3,718 | +6% | 0 | 0 | — |
case-01 | fail→pass | 25,389 | 24,098 | -5% | 1 | 1 | 0% | 6,211 | 7,648 | +23% | 0 | 0 | — |
case-02 | fail→fail | 26,093 | 24,795 | -5% | 1 | 1 | 0% | 6,210 | 7,647 | +23% | 0 | 0 | — |
case-03 | fail→pass | 26,096 | 25,483 | -2% | 1 | 1 | 0% | 6,205 | 7,642 | +23% | 0 | 0 | — |
case-04 | fail→fail | 16,710 | 7,240 | -57% | 1 | 1 | 0% | 3,055 | 2,965 | -3% | 0 | 0 | — |
case-07 | fail→pass | 12,297 | 5,885 | -52% | 1 | 1 | 0% | 2,283 | 2,601 | +14% | 0 | 0 | — |
case-08 | pass→pass | 8,940 | 3,172 | -65% | 1 | 1 | 0% | 1,721 | 2,055 | +19% | 0 | 0 | — |
case-09 | fail→pass | 11,566 | 8,803 | -24% | 1 | 1 | 0% | 1,963 | 2,911 | +48% | 0 | 0 | — |
case-10 | fail→fail | 12,759 | 8,788 | -31% | 1 | 1 | 0% | 2,469 | 2,981 | +21% | 0 | 0 | — |
case-11 | fail→pass | 13,271 | 7,100 | -46% | 1 | 1 | 0% | 2,340 | 2,828 | +21% | 0 | 0 | — |
case-12 | pass→pass | 10,065 | 10,276 | +2% | 1 | 1 | 0% | 2,014 | 3,549 | +76% | 0 | 0 | — |
case-13 | fail→pass | 11,116 | 5,930 | -47% | 1 | 1 | 0% | 2,164 | 2,677 | +24% | 0 | 0 | — |
case-14 | pass→pass | 10,362 | 7,754 | -25% | 1 | 1 | 0% | 1,835 | 2,792 | +52% | 0 | 0 | — |
case-15 | fail→pass | 14,204 | 5,401 | -62% | 1 | 1 | 0% | 2,737 | 2,626 | -4% | 0 | 0 | — |
case-16 | fail→pass | 11,920 | 6,292 | -47% | 1 | 1 | 0% | 1,990 | 2,564 | +29% | 0 | 0 | — |
case-17 | fail→fail | 10,333 | 2,118 | -80% | 1 | 1 | 0% | 1,831 | 1,832 | +0% | 0 | 0 | — |
case-18 | fail→pass | 5,636 | 1,666 | -70% | 1 | 1 | 0% | 1,166 | 1,750 | +50% | 0 | 0 | — |
case-19 | fail→pass | 6,281 | 2,292 | -64% | 1 | 1 | 0% | 1,235 | 1,920 | +55% | 0 | 0 | — |
case-20 | pass→pass | 14,159 | 22,349 | +58% | 1 | 1 | 0% | 3,375 | 6,809 | +102% | 0 | 0 | — |
case-21 | pass→pass | 12,356 | 14,274 | +16% | 1 | 1 | 0% | 2,787 | 5,073 | +82% | 0 | 0 | — |
case-22 | pass→fail | 10,900 | 18,027 | +65% | 1 | 1 | 0% | 2,380 | 5,348 | +125% | 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 +41 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.