Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, a
.claude/skills/rampstackco-accessibility-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 102% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 85% | 0% |
Run a thorough accessibility audit and produce a remediation plan. Stack-agnostic. Anchored to WCAG 2.1 AA, with notes on AAA where relevant.
This skill goes deeper than the accessibility checks in qa-testing and design-standards. Use this when accessibility itself is the goal.
qa-testing)frontend-component-build)design-standards or brand-identity)WCAG organizes accessibility around four principles. The audit covers each in depth.
Information and UI must be presentable in ways users can perceive.
Audit checks:
alt text. Decorative images use alt="". Complex images (charts, infographics) have long descriptions.UI components and navigation must be operable.
Audit checks:
Information and operation must be understandable.
Audit checks:
<html lang="...">). Unusual words and abbreviations have definitions or expansions. Reading level appropriate to audience.Content must be robust enough to work with current and future user agents.
Audit checks:
Run automated scanners across the priority pages. These catch 30 to 50 percent of issues but miss the rest.
Tools:
Output: A list of automated findings, by page.
Unplug the mouse. Navigate the priority user flows using only keyboard.
Test:
Document: Any flow where keyboard navigation breaks down.
Test with at least one real screen reader, or state the gap per the data-availability rule. Each combination has quirks.
Common combinations:
Test:
Verify the visual aspects of accessibility.
Test:
prefers-reduced-motion honored)Often overlooked. Critical for inclusive products.
Test:
references/audit-report-template.md.For prioritization:
Critical (P0):
Important (P1):
Minor (P2):
Polish (P3):
Default output is a comprehensive audit report at accessibility-audit.md.
Structure:
Plus a remediation tracking spreadsheet with one row per finding.
This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.
references/audit-report-template.md - Full audit report template.references/wcag-quick-reference.md - Condensed WCAG 2.1 AA criteria with audit checks.references/aria-patterns.md - Decision-grade ARIA patterns. Semantic-HTML-first principle, common interactive widgets (accordion, tabs, modal, toggle, disclosure, navigation), live regions, hiding patterns, labeling, state indicators, anti-patterns.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 32,796 | 32,457 | -1% | 1 | 1 | 0% | 6,225 | 8,619 | +38% | 0 | 0 | — |
case-02 | fail→fail | 31,954 | 32,990 | +3% | 1 | 1 | 0% | 6,088 | 8,602 | +41% | 0 | 0 | — |
case-03 | fail→pass | 33,871 | 32,040 | -5% | 1 | 1 | 0% | 6,203 | 8,210 | +32% | 0 | 0 | — |
case-04 | pass→pass | 12,339 | 18,020 | +46% | 1 | 1 | 0% | 2,328 | 5,494 | +136% | 0 | 0 | — |
case-05 | pass→pass | 21,086 | 19,610 | -7% | 1 | 1 | 0% | 4,702 | 6,654 | +42% | 0 | 0 | — |
case-06 | pass→pass | 14,666 | 30,172 | +106% | 1 | 1 | 0% | 2,811 | 8,570 | +205% | 0 | 0 | — |
case-07 | fail→pass | 11,733 | 9,557 | -19% | 1 | 1 | 0% | 1,972 | 3,975 | +102% | 0 | 0 | — |
case-08 | fail→pass | 10,307 | 5,451 | -47% | 1 | 1 | 0% | 1,767 | 3,357 | +90% | 0 | 0 | — |
case-09 | pass→pass | 14,590 | 10,518 | -28% | 1 | 1 | 0% | 2,364 | 4,036 | +71% | 0 | 0 | — |
case-10 | pass→pass | 13,410 | 13,956 | +4% | 1 | 1 | 0% | 2,207 | 4,524 | +105% | 0 | 0 | — |
case-11 | pass→pass | 13,766 | 11,890 | -14% | 1 | 1 | 0% | 2,053 | 4,269 | +108% | 0 | 0 | — |
case-12 | pass→pass | 16,115 | 12,155 | -25% | 1 | 1 | 0% | 2,659 | 4,510 | +70% | 0 | 0 | — |
case-13 | pass→pass | 18,576 | 19,159 | +3% | 1 | 1 | 0% | 3,079 | 5,445 | +77% | 0 | 0 | — |
case-14 | pass→pass | 6,447 | 5,357 | -17% | 1 | 1 | 0% | 1,259 | 3,370 | +168% | 0 | 0 | — |
case-15 | pass→pass | 17,974 | 18,493 | +3% | 1 | 1 | 0% | 2,619 | 5,153 | +97% | 0 | 0 | — |
case-16 | fail→pass | 12,912 | 8,931 | -31% | 1 | 1 | 0% | 1,929 | 3,577 | +85% | 0 | 0 | — |
case-17 | fail→pass | 13,124 | 4,449 | -66% | 1 | 1 | 0% | 2,054 | 3,149 | +53% | 0 | 0 | — |
case-18 | pass→pass | 15,365 | 6,911 | -55% | 1 | 1 | 0% | 2,124 | 3,369 | +59% | 0 | 0 | — |
case-19 | pass→pass | 13,415 | 10,094 | -25% | 1 | 1 | 0% | 2,224 | 4,015 | +81% | 0 | 0 | — |
case-20 | pass→pass | 17,220 | 16,637 | -3% | 1 | 1 | 0% | 2,873 | 5,195 | +81% | 0 | 0 | — |
case-21 | pass→pass | 19,044 | 16,404 | -14% | 1 | 1 | 0% | 3,209 | 5,174 | +61% | 0 | 0 | — |
case-22 | fail→fail | 16,621 | 14,756 | -11% | 1 | 1 | 0% | 2,865 | 4,831 | +69% | 0 | 0 | — |
case-23 | pass→pass | 16,036 | 13,534 | -16% | 1 | 1 | 0% | 2,805 | 4,551 | +62% | 0 | 0 | — |
case-24 | pass→pass | 15,790 | 14,889 | -6% | 1 | 1 | 0% | 2,543 | 4,801 | +89% | 0 | 0 | — |
case-25 | pass→pass | 11,058 | 10,183 | -8% | 1 | 1 | 0% | 1,613 | 3,809 | +136% | 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. 25 cases were attempted. The headline lift of +24 percentage points is the difference between those two pass rates over the 25 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.