Skip to main content
idapt
HomeAI ModelsPricing
Sign inStart free
All prompts

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.

DesignAnalyzeSuggested model: anthropic/claude-sonnet-5

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

VariableWhat it isExample
{{screen}}The screen, spec, or markup[paste the component markup or describe the screen precisely]
{{standard}}The bar to meetWCAG 2.2 AA

Frequently asked

Related prompts

Write design handoff annotations developers can build fromOutline a user flow with its failure pathsReview a diff like a senior engineer

Ready to get to work?

Free to start. No credit card. Never trained on your data.

Start free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)