Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate accessibility compliance reports including VPAT and ACR documents
.claude/skills/a5c-ai-accessibility-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -76% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -86% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 39% | 0% |
Generate comprehensive accessibility compliance reports including VPAT (Voluntary Product Accessibility Template) and ACR (Accessibility Conformance Report) documents.
json{ "type": "object", "properties": { "reportType": { "type": "string", "enum": ["vpat", "acr", "wcag-checklist", "remediation-roadmap"], "default": "vpat" }, "productName": { "type": "string", "description": "Name of the product being evaluated" }, "productVersion": { "type": "string", "description": "Version of the product" }, "evaluationDate": { "type": "string", "format": "date" }, "wcagLevel": { "type": "string", "enum": ["A", "AA", "AAA"], "default": "AA" }, "auditResults": { "type": "array", "items": { "type": "object", "properties": { "criterion": { "type": "string" }, "level": { "type": "string" }, "conformance": { "type": "string" }, "remarks": { "type": "string" } } } }, "outputFormat": { "type": "string", "enum": ["docx", "pdf", "html", "markdown"], "default": "markdown" } }, "required": ["reportType", "productName", "auditResults"] }
json{ "type": "object", "properties": { "reportPath": { "type": "string", "description": "Path to generated report" }, "summary": { "type": "object", "properties": { "overallConformance": { "type": "string" }, "criteriaPass": { "type": "number" }, "criteriaFail": { "type": "number" }, "criteriaPartial": { "type": "number" } } }, "remediationItems": { "type": "array", "description": "Prioritized remediation tasks" }, "timeline": { "type": "object", "description": "Suggested remediation timeline" } } }
javascriptconst result = await skill.execute({ reportType: 'vpat', productName: 'MyApp Web Portal', productVersion: '2.1.0', wcagLevel: 'AA', auditResults: [ { criterion: '1.1.1', level: 'A', conformance: 'Supports', remarks: 'All images have alt text' }, { criterion: '1.4.3', level: 'AA', conformance: 'Partially Supports', remarks: 'Some low contrast text in footer' } ], outputFormat: 'markdown' });
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | fail→pass | 33,901 | 21,614 | -36% | 1 | 1 | 0% | 6,548 | 3,711 | -43% | 0 | 0 | — |
case-06 | pass→pass | 12,727 | 14,481 | +14% | 1 | 1 | 0% | 1,315 | 2,523 | +92% | 0 | 0 | — |
case-01 | pass→pass | 32,618 | 19,404 | -41% | 1 | 1 | 0% | 2,588 | 3,500 | +35% | 0 | 0 | — |
case-02 | fail→pass | 59,038 | 15,950 | -73% | 1 | 1 | 0% | 12,670 | 3,037 | -76% | 0 | 0 | — |
case-03 | fail→pass | 32,384 | 12,632 | -61% | 1 | 1 | 0% | 6,110 | 2,410 | -61% | 0 | 0 | — |
case-04 | pass→pass | 22,112 | 17,918 | -19% | 1 | 1 | 0% | 2,013 | 3,611 | +79% | 0 | 0 | — |
case-05 | pass→pass | 23,758 | 12,407 | -48% | 1 | 1 | 0% | 3,525 | 2,179 | -38% | 0 | 0 | — |
case-07 | fail→pass | 59,214 | 9,010 | -85% | 1 | 1 | 0% | 11,413 | 1,633 | -86% | 0 | 0 | — |
case-08 | fail→pass | 13,828 | 12,436 | -10% | 1 | 1 | 0% | 1,719 | 2,397 | +39% | 0 | 0 | — |
case-09 | fail→pass | 16,279 | 11,038 | -32% | 1 | 1 | 0% | 1,993 | 2,068 | +4% | 0 | 0 | — |
case-10 | pass→pass | 24,221 | 16,743 | -31% | 1 | 1 | 0% | 3,841 | 3,543 | -8% | 0 | 0 | — |
case-11 | pass→fail | 41,216 | 19,838 | -52% | 1 | 1 | 0% | 8,223 | 3,565 | -57% | 0 | 0 | — |
case-13 | pass→fail | 45,336 | 14,367 | -68% | 1 | 1 | 0% | 7,968 | 2,572 | -68% | 0 | 0 | — |
case-14 | pass→pass | 43,690 | 23,335 | -47% | 1 | 1 | 0% | 6,090 | 4,886 | -20% | 0 | 0 | — |
case-15 | pass→pass | 31,782 | 53,480 | +68% | 1 | 1 | 0% | 2,984 | 7,088 | +138% | 0 | 0 | — |
case-16 | pass→pass | 26,165 | 20,199 | -23% | 1 | 1 | 0% | 4,103 | 3,463 | -16% | 0 | 0 | — |
case-17 | fail→pass | 24,707 | 38,641 | +56% | 1 | 1 | 0% | 3,201 | 3,081 | -4% | 0 | 0 | — |
case-18 | fail→fail | 20,991 | 22,503 | +7% | 1 | 1 | 0% | 3,414 | 3,990 | +17% | 0 | 0 | — |
case-19 | pass→fail | 11,712 | 14,448 | +23% | 1 | 1 | 0% | 2,332 | 2,525 | +8% | 0 | 0 | — |
case-20 | pass→pass | 13,980 | 20,525 | +47% | 1 | 1 | 0% | 2,092 | 2,828 | +35% | 0 | 0 | — |
case-21 | fail→fail | 10,460 | 15,807 | +51% | 1 | 1 | 0% | 2,044 | 3,726 | +82% | 0 | 0 | — |
case-22 | fail→fail | 62,291 | 15,070 | -76% | 1 | 1 | 0% | 2,746 | 3,966 | +44% | 0 | 0 | — |
case-23 | fail→pass | 8,762 | 5,643 | -36% | 1 | 1 | 0% | 1,453 | 1,911 | +32% | 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. 23 cases were attempted. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 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.