Skip to content

Generate a WCAG 2.2 AA Accessibility Test Suite with AI

Updated 2026-06-08·intermediate·Accessibility Testing

Returns a comprehensive WCAG 2.2 AA test suite organized by Success Criterion (perceivable / operable / understandable / robust) — each item with SC number, test method (manual / axe / Playwright @axe-core), pass criteria, and explicit coverage of WCAG 2.2's new criteria.

When to use it

  • Auditing accessibility on an existing product against WCAG 2.2 AA.
  • Building an accessibility test plan for a new feature or release.
  • Onboarding engineers to accessibility testing fundamentals.
  • Documenting accessibility coverage for compliance (EAA, ADA, AODA).

The prompt

XML-tagged — best for Claude 4.x

<role>
You are an accessibility specialist. You cite WCAG Success Criteria by number (e.g., SC 1.4.3) and you know which criteria are automatable vs require manual judgment.
</role>

<context>
WCAG 2.2 AA includes all 2.1 AA criteria PLUS 6 new criteria added in 2.2:
- SC 2.4.11 Focus Not Obscured (Minimum) — AA
- SC 2.5.7 Dragging Movements — AA
- SC 2.5.8 Target Size (Minimum) — AA
- SC 3.2.6 Consistent Help — A
- SC 3.3.7 Redundant Entry — A
- SC 3.3.8 Accessible Authentication (Minimum) — AA

Test methods:
- **axe / Playwright @axe-core/playwright** — automated, ~40% coverage
- **Manual** — keyboard testing, screen reader, judgment-based criteria
- **Mixed** — axe finds, human verifies

Each Success Criterion has DEFINITIVE pass criteria — not opinions.
</context>

<task>
For the application below, generate a WCAG 2.2 AA test suite organized by principle:
1. **Perceivable** (Principle 1) — covers SCs 1.x
2. **Operable** (Principle 2) — covers SCs 2.x
3. **Understandable** (Principle 3) — covers SCs 3.x
4. **Robust** (Principle 4) — covers SCs 4.x

For each Success Criterion in scope, include:
- SC number and name
- Test method (axe / Manual / Mixed)
- Pass criteria (specific, measurable)
- Common failure pattern

Explicitly cover the 6 new WCAG 2.2 criteria.
</task>

<input>
Application description: {app}
Tech stack and surface (web / mobile native / hybrid): {stack}
Out-of-scope (specific components/pages): {out_of_scope}
</input>

<constraints>
- SC numbers MUST be cited (e.g., "SC 1.4.3 Contrast Minimum").
- Test method per item: axe / Manual / Mixed.
- Pass criteria specific and measurable, not "looks accessible".
- Include ALL 6 WCAG 2.2 new criteria.
- Group by principle (Perceivable / Operable / Understandable / Robust).
- Coverage estimate (% automatable vs manual) at the end.
</constraints>

<output_format>
Markdown document with 4 H2 sections (one per principle), each containing a table: SC | Name | Test method | Pass criteria | Common failure. Followed by a "WCAG 2.2 new criteria highlights" section and a "Coverage summary" with automatable %.
</output_format>

Before writing, identify which Success Criteria are NOT applicable to this stack (e.g., audio criteria if no audio content) — list as out-of-scope rather than padding the table.

Example

Common pitfalls

  • Model uses WCAG 2.1 criteria only and skips the 6 new 2.2 SCs — explicitly require them in constraints.
  • Test method defaults to 'manual' for everything — under-recognizes axe coverage.
  • Pass criteria gets vague ('looks accessible'); require measurable specifics.
  • Out-of-scope SCs (audio for text-only apps) get padded into the table; force out-of-scope to be acknowledged separately.

Tips

  • Run axe in CI on every PR; gates the 40% that can be automated. Manual SCs covered quarterly.
  • Use Playwright @axe-core/playwright for component-level a11y testing — finds issues E2E doesn't see.
  • Pair with `keyboard-nav-test-cases` and `screen-reader-scenarios` for the manual portion.
  • Re-baseline annually as WCAG evolves (4.0 work in progress).

FAQ

2.2 adds 6 new criteria, mostly focused on cognitive accessibility and mobile/touch interfaces. If you're at 2.1 AA, the new criteria are small additions — but the legal landscape (EAA, ADA enforcement) often requires 2.2 by mid-2025.

Related prompts