Audit intermediate Works with: Any AI

Screen Reader Label and Order Audit for an App Screen

Table output

Check labels and reading order on a screen.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Rate this prompt

Loading ratings…

Audit a screen. List of elements in visual order with their accessibility labels and roles: [ELEMENT_LIST]. Platform: [PLATFORM].

Check that every control has a clear label, state and role, images have descriptions or are hidden if decorative, grouped items read together sensibly, reading order matches visual order, and custom components expose their behaviour.

Return a table with Element, Issue and Fix and a short test plan using the platform's built-in screen reader [VERIFY].

Add a worked audit of an invented screen. Elements in visual order: back button with no label, announced as button, fail; screen title as a heading, pass; photo of a product with the filename as its label, fail; price text, pass; add to basket button, pass; quantity stepper with plus and minus icons announced only as button, fail because the purpose and current value are missing; a tab bar with the selected tab not announced as selected, fail. Count: 4 fails of 7 elements, 57 percent. Fixes: label the back button Back, give the image a short description, label the stepper buttons Increase quantity and Decrease quantity and announce the value, and expose the selected state. Reading order check: the price is announced before the product name, which is confusing; reorder. Provide platform-neutral wording for roles and states and ask me to verify the exact property names for my platform [VERIFY]. Add a test script: turn on the screen reader, swipe through the screen, record what is spoken, and compare with the expected text. Suggest involving users of screen readers in testing, compensated fairly. Provide a defect template with screen, element, expected, observed, severity and fix. Remind me that custom components need extra care and that dynamic changes such as loading messages should be announced.

Finish with a severity rule: a missing label on a control needed to complete a core task is high; a verbose label is low. Count the issues by severity and report the totals so the team can plan the fixes in order and track the number of open items each week.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Related prompts