B. Quality, Speed & Resilience · Prompt 16

Accessibility Pass

Get the free PDF

Why it matters

Accessibility failures exclude people. Some laws and app stores also treat them as compliance issues.

Modeled on

axe-core, Deque's open-source accessibility engine.

How to run this prompt

Switch to a mode that does not edit files. In Cursor that is Ask or Plan. In Claude Code that is Plan mode.
Paste the audit prompt. Wait for the report. It must stop and ask which IDs to fix.
Read the report. Keep the IDs you agree with.
Switch to a mode that can edit. Paste the fix prompt and the IDs you chose.
Switch back to the read-only mode and paste the same audit prompt again. Confirm those IDs are gone.

Cursor: audit in Ask mode or Plan mode. Fix in Agent mode.
Claude Code: audit in Plan mode (Shift+Tab cycles to it). Fix in Normal mode, which can edit.
Any other tool: audit in Chat, Discuss, or Plan mode, whichever answers without editing files. If the tool has no such mode, the prompt itself forbids edits. Fix in the mode that is allowed to edit files.

The audit prompt

MODE: AUDIT ONLY. Do not create, edit, or delete any file. Do not run commands
that change anything: no installs, migrations, git commits, deploys, or "--fix" flags.
If your tool has an Ask, Plan, Chat, or Discuss mode, use it for this prompt.

Before you start:
- Tell me the stack you detect (framework, language, database, auth, hosting,
  payment provider) and which folders you will review.
- If a check below does not apply to this stack, write "Not applicable" and why.
- If you can run read-only commands, run the ones listed. If you cannot, list them
  so I can run them and paste the output.

Accessibility Pass: what to check
Audit the frontend for issues a keyboard-only or screen-reader user would hit. Do not claim WCAG conformance. List concrete issues.
1. Check images. Meaningful images need a useful alt. Decorative images need an empty alt. Flag alt text that repeats the file name or says "image".
2. Check controls built from div or span that are clickable but have no button or link role, no keyboard handler, and no accessible name.
3. Check contrast. WCAG 2.2 AA is 4.5:1 for normal text and 3:1 for large text (18pt or 14pt bold) and for UI component boundaries. Name the colors if you can see them in CSS. If you cannot compute the ratio, say so.
4. Check that every control is reachable by keyboard and has a visible focus style. Flag outline: none with no replacement.
5. Check inputs for a label tied with for and id, or an aria-label. Placeholder text is not a label.
6. Check toasts, live counts, and loading states for an aria-live region. A message that only appears visually is easy to miss.
7. Check heading order and that the page has one h1. Flag skipped levels only when they make the page harder to follow.
8. If you can run a local axe scan in a read-only way, summarize it and still list the issues above in your own words. If you cannot, say the scan is Needs manual check.

Evidence rules:
- Every finding cites a file path and line number, or the exact command output used.
- Mark each finding Confirmed (seen in the code) or Needs manual check (depends on
  something outside the repo, such as a dashboard setting or production data).
- Never print a full secret. Show the first 4 characters and the location only.
- If you are not sure, say so. Do not invent files, settings, or results.

Severity: Critical = exploitable now, or leaks real data or money. High = serious
with little effort. Medium = weakens defenses or needs a second bug. Low = hygiene.

Report:
- Summary: count of findings by severity.
- Table: ID | Severity | Confirmed? | Finding | Evidence | Why it matters | Suggested fix | Effort
  (IDs for this prompt use the prefix P16, for example P16-1, P16-2.)
- Checked and fine: what you verified is already OK.
- Could not check: what I need to look at myself, and where.

Then stop. Do not fix anything. Ask me which IDs I want fixed.

Get the free PDF

Related prompts

Share this prompt

WhatsApp LinkedIn X

How to run this prompt

Switch to a mode that does not edit files. In Cursor that is Ask or Plan. In Claude Code that is Plan mode.

Paste the audit prompt. Wait for the report. It must stop and ask which IDs to fix.

Read the report. Keep the IDs you agree with.

Switch to a mode that can edit. Paste the fix prompt and the IDs you chose.

Switch back to the read-only mode and paste the same audit prompt again. Confirm those IDs are gone.

Cursor: audit in Ask mode or Plan mode. Fix in Agent mode.

Claude Code: audit in Plan mode (Shift+Tab cycles to it). Fix in Normal mode, which can edit.

Any other tool: audit in Chat, Discuss, or Plan mode, whichever answers without editing files. If the tool has no such mode, the prompt itself forbids edits. Fix in the mode that is allowed to edit files.

The audit prompt

MODE: AUDIT ONLY. Do not create, edit, or delete any file. Do not run commands that change anything: no installs, migrations, git commits, deploys, or "--fix" flags. If your tool has an Ask, Plan, Chat, or Discuss mode, use it for this prompt. Before you start: - Tell me the stack you detect (framework, language, database, auth, hosting, payment provider) and which folders you will review. - If a check below does not apply to this stack, write "Not applicable" and why. - If you can run read-only commands, run the ones listed. If you cannot, list them so I can run them and paste the output. Accessibility Pass: what to check Audit the frontend for issues a keyboard-only or screen-reader user would hit. Do not claim WCAG conformance. List concrete issues. 1. Check images. Meaningful images need a useful alt. Decorative images need an empty alt. Flag alt text that repeats the file name or says "image". 2. Check controls built from div or span that are clickable but have no button or link role, no keyboard handler, and no accessible name. 3. Check contrast. WCAG 2.2 AA is 4.5:1 for normal text and 3:1 for large text (18pt or 14pt bold) and for UI component boundaries. Name the colors if you can see them in CSS. If you cannot compute the ratio, say so. 4. Check that every control is reachable by keyboard and has a visible focus style. Flag outline: none with no replacement. 5. Check inputs for a label tied with for and id, or an aria-label. Placeholder text is not a label. 6. Check toasts, live counts, and loading states for an aria-live region. A message that only appears visually is easy to miss. 7. Check heading order and that the page has one h1. Flag skipped levels only when they make the page harder to follow. 8. If you can run a local axe scan in a read-only way, summarize it and still list the issues above in your own words. If you cannot, say the scan is Needs manual check. Evidence rules: - Every finding cites a file path and line number, or the exact command output used. - Mark each finding Confirmed (seen in the code) or Needs manual check (depends on something outside the repo, such as a dashboard setting or production data). - Never print a full secret. Show the first 4 characters and the location only. - If you are not sure, say so. Do not invent files, settings, or results. Severity: Critical = exploitable now, or leaks real data or money. High = serious with little effort. Medium = weakens defenses or needs a second bug. Low = hygiene. Report: - Summary: count of findings by severity. - Table: ID | Severity | Confirmed? | Finding | Evidence | Why it matters | Suggested fix | Effort (IDs for this prompt use the prefix P16, for example P16-1, P16-2.) - Checked and fine: what you verified is already OK. - Could not check: what I need to look at myself, and where. Then stop. Do not fix anything. Ask me which IDs I want fixed.