Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →WCAG AAA conformance specialist. Audits web content against WCAG 2.2 Level AAA success criteria beyond the standard AA target. Covers enhanced contrast (7:1), extended audio descriptions, sign language, reading level, abbreviations, pronunciation, and focus appearance.
.claude/skills/community-access-wcag-aaa-2811f1/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 43% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 24% | 0% |
You audit web content against WCAG 2.2 Level AAA success criteria — the highest conformance level.
AAA conformance is not required by most legal frameworks. Confirm AA conformance first.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,275 | 11,925 | -22% | 1 | 1 | 0% | 2,588 | 2,411 | -7% | 0 | 0 | — |
case-02 | fail→pass | 32,987 | 23,946 | -27% | 1 | 1 | 0% | 5,608 | 4,370 | -22% | 0 | 0 | — |
case-03 | pass→pass | 5,704 | 5,338 | -6% | 1 | 1 | 0% | 901 | 1,284 | +43% | 0 | 0 | — |
case-04 | pass→pass | 9,117 | 8,046 | -12% | 1 | 1 | 0% | 1,425 | 1,769 | +24% | 0 | 0 | — |
case-05 | pass→pass | 7,404 | 7,212 | -3% | 1 | 1 | 0% | 1,270 | 1,613 | +27% | 0 | 0 | — |
case-06 | fail→pass | 9,748 | 10,690 | +10% | 1 | 1 | 0% | 1,767 | 2,388 | +35% | 0 | 0 | — |
case-15 | pass→pass | 8,517 | 7,907 | -7% | 1 | 1 | 0% | 1,404 | 1,774 | +26% | 0 | 0 | — |
case-07 | pass→pass | 7,479 | 9,092 | +22% | 1 | 1 | 0% | 1,279 | 1,952 | +53% | 0 | 0 | — |
case-08 | pass→pass | 6,452 | 7,139 | +11% | 1 | 1 | 0% | 998 | 1,458 | +46% | 0 | 0 | — |
case-09 | pass→pass | 10,938 | 10,770 | -2% | 1 | 1 | 0% | 1,722 | 2,033 | +18% | 0 | 0 | — |
case-10 | pass→pass | 16,380 | 16,100 | -2% | 1 | 1 | 0% | 2,979 | 3,118 | +5% | 0 | 0 | — |
case-21 | pass→pass | 12,116 | 10,783 | -11% | 1 | 1 | 0% | 1,916 | 2,207 | +15% | 0 | 0 | — |
case-11 | pass→pass | 6,320 | 8,297 | +31% | 1 | 1 | 0% | 1,102 | 1,814 | +65% | 0 | 0 | — |
case-12 | pass→pass | 8,351 | 10,854 | +30% | 1 | 1 | 0% | 1,477 | 2,180 | +48% | 0 | 0 | — |
case-13 | pass→pass | 9,710 | 10,666 | +10% | 1 | 1 | 0% | 1,608 | 2,055 | +28% | 0 | 0 | — |
case-14 | pass→pass | 9,731 | 10,269 | +6% | 1 | 1 | 0% | 1,663 | 2,163 | +30% | 0 | 0 | — |
case-16 | pass→pass | 4,668 | 6,762 | +45% | 1 | 1 | 0% | 773 | 1,476 | +91% | 0 | 0 | — |
case-17 | pass→pass | 5,954 | 7,031 | +18% | 1 | 1 | 0% | 908 | 1,570 | +73% | 0 | 0 | — |
case-18 | pass→pass | 10,386 | 11,852 | +14% | 1 | 1 | 0% | 1,664 | 2,366 | +42% | 0 | 0 | — |
case-19 | pass→pass | 23,490 | 18,477 | -21% | 1 | 1 | 0% | 3,765 | 3,568 | -5% | 0 | 0 | — |
case-20 | pass→pass | 11,669 | 13,200 | +13% | 1 | 1 | 0% | 2,001 | 2,536 | +27% | 0 | 0 | — |
case-22 | pass→pass | 11,840 | 11,244 | -5% | 1 | 1 | 0% | 1,848 | 2,187 | +18% | 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.
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.