Prompt library
Review a screen for accessibility
Per-element verdicts with computed contrast ratios produce a fixable punch list instead of an awareness lecture. The cannot-assess candor matters: static reviews systematically miss focus order and announcement bugs, and saying which tool catches each keeps the checklist from breeding false confidence.
Last reviewed July 17, 2026
The prompt
Review the screen below for accessibility.
The screen (describe or paste the spec/markup): {{screen}}
Target standard: {{standard}}
Work through, reporting violation / pass / cannot-assess per item with the specific element named:
1. Perceivable: text contrast against its actual background (compute ratios where I gave colors; flag anything under 4.5:1 for body text, 3:1 for large), meaning carried by color alone, text alternatives for informative images, and whether text scales to 200 percent without loss.
2. Operable: full keyboard path in a stated order, visible focus indicators, touch targets at 24px minimum, no keyboard traps, and time limits with extensions.
3. Understandable: labels attached to inputs (not placeholder-as-label), error messages that say what happened and how to fix it, and predictable navigation.
4. Robust: semantic roles for interactive elements, announced state changes (loading, success, expansion), and heading hierarchy without skips.
Then: the 3 violations to fix first, ranked by how many users each blocks outright, and the one-line fix per item. Mark plainly what a static review cannot assess (screen reader flow, actual focus order) and what tool or test covers each.Run in idaptOpens a new chat with the prompt prefilled. Nothing sends until you press send.
Fill in the variables
| Variable | What it is | Example |
|---|---|---|
| {{screen}} | The screen, spec, or markup | [paste the component markup or describe the screen precisely] |
| {{standard}} | The bar to meet | WCAG 2.2 AA |