Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit a component or page for accessibility issues and fix them
.claude/skills/bilal140202-ss-a11y/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -10% | 0% |
/ss-review/ss-auditdata-slot, no semantic tokens) — assumes StyleSeed conventionsTarget: $ARGUMENTS
text-muted-foreground (#717182) on bg-background (#FFFFFF) = 4.6:1 (passes)text-brand on white (verify contrast with your skin's brand color)<img> need alt, icons need aria-label when meaningfulmin-h-11 min-w-11)h-9 (36px) buttons — should be h-11w-11 h-11focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2prefers-reduced-motioncss @media (prefers-reduced-motion: reduce) { *, *::before, *::after { animation-duration: 0.01ms !important; transition-duration: 0.01ms !important; } }
aria-labelaria-describedby)<html lang="en"> (or appropriate language code for your project)<button>, <nav>, <main>, <header>)role attributes| Token | Minimum Contrast | Note | |-------|-----------------|------| | --foreground | 7:1+ | Body text — verify with your skin | | --muted-foreground | 4.5:1+ | Secondary text — verify with your skin | | --brand | 4.5:1+ | Accent — verify with your skin's brand color | | --destructive | 4.5:1+ | Error — verify with your skin | | --success | 3:1+ | Large text/icons only — verify with your skin | | --warning | 4.5:1+ | Warning text — some skins need a darker variant |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→pass | 15,390 | 7,876 | -49% | 1 | 1 | 0% | 2,643 | 2,260 | -14% | 0 | 0 | — |
case-22 | fail→pass | 13,739 | 10,541 | -23% | 1 | 1 | 0% | 2,367 | 2,703 | +14% | 0 | 0 | — |
case-01 | fail→pass | 18,819 | 24,435 | +30% | 1 | 1 | 0% | 3,459 | 4,092 | +18% | 0 | 0 | — |
case-02 | fail→fail | 17,774 | 7,427 | -58% | 1 | 1 | 0% | 3,154 | 1,295 | -59% | 0 | 0 | — |
case-03 | fail→fail | 19,502 | 7,605 | -61% | 1 | 1 | 0% | 3,482 | 1,113 | -68% | 0 | 0 | — |
case-04 | fail→pass | 16,695 | 11,400 | -32% | 1 | 1 | 0% | 3,151 | 2,905 | -8% | 0 | 0 | — |
case-06 | pass→fail | 7,156 | 5,435 | -24% | 1 | 1 | 0% | 1,242 | 1,138 | -8% | 0 | 0 | — |
case-07 | fail→pass | 12,324 | 7,607 | -38% | 1 | 1 | 0% | 2,320 | 2,091 | -10% | 0 | 0 | — |
case-08 | pass→pass | 14,444 | 11,779 | -18% | 1 | 1 | 0% | 2,591 | 3,140 | +21% | 0 | 0 | — |
case-09 | fail→pass | 7,638 | 15,165 | +99% | 1 | 1 | 0% | 1,195 | 3,760 | +215% | 0 | 0 | — |
case-10 | pass→pass | 10,188 | 17,510 | +72% | 1 | 1 | 0% | 1,674 | 3,353 | +100% | 0 | 0 | — |
case-11 | pass→pass | 16,587 | 13,616 | -18% | 1 | 1 | 0% | 2,792 | 2,980 | +7% | 0 | 0 | — |
case-12 | pass→pass | 15,530 | 18,898 | +22% | 1 | 1 | 0% | 2,554 | 3,665 | +44% | 0 | 0 | — |
case-13 | pass→pass | 13,840 | 14,427 | +4% | 1 | 1 | 0% | 2,521 | 3,785 | +50% | 0 | 0 | — |
case-14 | pass→pass | 18,275 | 14,097 | -23% | 1 | 1 | 0% | 3,219 | 3,273 | +2% | 0 | 0 | — |
case-15 | fail→pass | 8,011 | 22,623 | +182% | 1 | 1 | 0% | 1,200 | 4,542 | +279% | 0 | 0 | — |
case-16 | pass→pass | 8,873 | 12,672 | +43% | 1 | 1 | 0% | 1,277 | 2,702 | +112% | 0 | 0 | — |
case-17 | fail→fail | 3,484 | 5,509 | +58% | 1 | 1 | 0% | 433 | 1,018 | +135% | 0 | 0 | — |
case-18 | fail→fail | 8,822 | 5,381 | -39% | 1 | 1 | 0% | 1,480 | 1,590 | +7% | 0 | 0 | — |
case-19 | pass→pass | 14,416 | 10,021 | -30% | 1 | 1 | 0% | 2,590 | 2,752 | +6% | 0 | 0 | — |
case-20 | fail→pass | 6,123 | 16,697 | +173% | 1 | 1 | 0% | 952 | 3,865 | +306% | 0 | 0 | — |
case-21 | fail→pass | 8,835 | 14,442 | +63% | 1 | 1 | 0% | 1,314 | 3,046 | +132% | 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, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +36 percentage points is the difference between those two pass rates over the 18 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.