Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply diagonal-cut corners and chamfered edges to buttons, cards, panels, and container shells. Use when a design needs precise geometric framing, sci-fi UI surfaces, clipped-corner controls, or engineered sharp containers instead of rounded pills or plain rectangles.
.claude/skills/mengto-corner-diagonals/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 10% | 0% |
css:root { --corner-cut-sm: 8px; --corner-cut-md: 14px; --corner-cut-lg: 24px; --corner-line: rgba(255, 255, 255, 0.18); --corner-line-strong: rgba(255, 255, 255, 0.34); --corner-fill: rgba(10, 14, 24, 0.82); --corner-accent: #8b5cf6; }
Use clip-path: polygon(...) for true diagonal silhouettes.
css.cut-all { --cut: var(--corner-cut-md); clip-path: polygon( var(--cut) 0, calc(100% - var(--cut)) 0, 100% var(--cut), 100% calc(100% - var(--cut)), calc(100% - var(--cut)) 100%, var(--cut) 100%, 0 calc(100% - var(--cut)), 0 var(--cut) ); } .cut-top-left-bottom-right { --cut: var(--corner-cut-md); clip-path: polygon( var(--cut) 0, 100% 0, 100% calc(100% - var(--cut)), calc(100% - var(--cut)) 100%, 0 100%, 0 var(--cut) ); } .cut-top-right-bottom-left { --cut: var(--corner-cut-md); clip-path: polygon( 0 0, calc(100% - var(--cut)) 0, 100% var(--cut), 100% 100%, var(--cut) 100%, 0 100%, 0 0 ); }
For bordered surfaces, use an outer wrapper and inner surface with the same polygon.
css.cut-shell { --cut: var(--corner-cut-md); --border-size: 1px; position: relative; padding: var(--border-size); background: linear-gradient(135deg, var(--corner-line-strong), transparent 46%, var(--corner-line)); clip-path: polygon( var(--cut) 0, 100% 0, 100% calc(100% - var(--cut)), calc(100% - var(--cut)) 100%, 0 100%, 0 var(--cut) ); } .cut-shell__inner { min-height: 100%; padding: clamp(16px, 2.4vw, 28px); background: var(--corner-fill); clip-path: inherit; }
html<section class="cut-shell"> <div class="cut-shell__inner"> ... </div> </section>
css.cut-button { --cut: var(--corner-cut-sm); position: relative; display: inline-flex; min-height: 44px; align-items: center; justify-content: center; gap: 8px; padding: 0 18px; border: 0; color: white; background: linear-gradient(135deg, var(--corner-accent), color-mix(in srgb, var(--corner-accent), black 28%)); clip-path: polygon( var(--cut) 0, 100% 0, 100% calc(100% - var(--cut)), calc(100% - var(--cut)) 100%, 0 100%, 0 var(--cut) ); } .cut-button:hover { filter: brightness(1.08); } .cut-button:focus-visible { outline: 2px solid color-mix(in srgb, var(--corner-accent), white 45%); outline-offset: 3px; }
Use a darker shell with diagonal outline treatment.
css.cut-button-secondary { --cut: var(--corner-cut-sm); color: white; background: linear-gradient(var(--corner-fill), var(--corner-fill)) padding-box, linear-gradient(135deg, var(--corner-line-strong), transparent 58%, var(--corner-accent)) border-box; border: 1px solid transparent; clip-path: polygon( var(--cut) 0, 100% 0, 100% calc(100% - var(--cut)), calc(100% - var(--cut)) 100%, 0 100%, 0 var(--cut) ); }
6px-10px for small controls, 12px-18px for cards, 20px-32px for large panels.44px height for touch targets.--cut scale.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,296 | 15,052 | -18% | 1 | 1 | 0% | 4,103 | 5,401 | +32% | 0 | 0 | — |
case-02 | fail→fail | 20,780 | 20,931 | +1% | 1 | 1 | 0% | 4,309 | 6,590 | +53% | 0 | 0 | — |
case-03 | fail→fail | 11,867 | 9,462 | -20% | 1 | 1 | 0% | 2,716 | 3,896 | +43% | 0 | 0 | — |
case-04 | fail→pass | 14,091 | 9,096 | -35% | 1 | 1 | 0% | 2,772 | 3,482 | +26% | 0 | 0 | — |
case-05 | fail→pass | 17,971 | 12,790 | -29% | 1 | 1 | 0% | 3,756 | 4,804 | +28% | 0 | 0 | — |
case-06 | fail→pass | 9,509 | 5,665 | -40% | 1 | 1 | 0% | 1,940 | 3,247 | +67% | 0 | 0 | — |
case-21 | pass→fail | 11,168 | 23,925 | +114% | 1 | 1 | 0% | 2,145 | 7,961 | +271% | 0 | 0 | — |
case-07 | fail→pass | 6,470 | 4,733 | -27% | 1 | 1 | 0% | 1,488 | 2,964 | +99% | 0 | 0 | — |
case-08 | fail→pass | 13,953 | 5,148 | -63% | 1 | 1 | 0% | 2,533 | 2,783 | +10% | 0 | 0 | — |
case-09 | fail→fail | 18,015 | 16,719 | -7% | 1 | 1 | 0% | 3,377 | 5,091 | +51% | 0 | 0 | — |
case-10 | fail→fail | 11,241 | 10,573 | -6% | 1 | 1 | 0% | 2,084 | 3,890 | +87% | 0 | 0 | — |
case-11 | fail→pass | 20,620 | 11,347 | -45% | 1 | 1 | 0% | 4,385 | 4,212 | -4% | 0 | 0 | — |
case-22 | pass→pass | 10,620 | 11,830 | +11% | 1 | 1 | 0% | 2,296 | 4,294 | +87% | 0 | 0 | — |
case-12 | fail→pass | 11,579 | 3,383 | -71% | 1 | 1 | 0% | 2,355 | 2,550 | +8% | 0 | 0 | — |
case-13 | pass→pass | 14,473 | 11,953 | -17% | 1 | 1 | 0% | 2,865 | 4,090 | +43% | 0 | 0 | — |
case-14 | pass→fail | 10,882 | 2,795 | -74% | 1 | 1 | 0% | 1,715 | 2,246 | +31% | 0 | 0 | — |
case-15 | fail→pass | 14,027 | 11,081 | -21% | 1 | 1 | 0% | 2,356 | 3,646 | +55% | 0 | 0 | — |
case-16 | fail→fail | 8,462 | 1,378 | -84% | 1 | 1 | 0% | 1,616 | 2,013 | +25% | 0 | 0 | — |
case-17 | pass→pass | 16,320 | 14,031 | -14% | 1 | 1 | 0% | 2,960 | 4,511 | +52% | 0 | 0 | — |
case-18 | pass→pass | 11,672 | 9,323 | -20% | 1 | 1 | 0% | 2,199 | 3,723 | +69% | 0 | 0 | — |
case-19 | pass→pass | 13,800 | 10,929 | -21% | 1 | 1 | 0% | 2,372 | 3,830 | +61% | 0 | 0 | — |
case-20 | pass→fail | 14,656 | 17,354 | +18% | 1 | 1 | 0% | 2,791 | 5,277 | +89% | 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 +23 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.