C. Website Launch Readiness · Prompt 26

Conversion & CTA Audit

Get the free PDF

Why it matters

A site can look finished and still give a visitor no clear next step.

Modeled on

Conversion checks: one primary action, a clear message, and a short form.

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.

Conversion & CTA Audit: what to check
Review clarity and the primary action, page by page. Do not rewrite the site in this pass. Suggest copy. Do not invent testimonials or numbers.
1. For each page, state the one primary action in a sentence, then say whether a clear control for it is visible without scrolling, on a wide window and on a 320px window.
2. Say whether the headline and the line under it tell a new visitor what this is, who it is for, and what they get.
3. If there is a sticky mobile bar, say whether it covers content or the keyboard. If a long page has no sticky action, say whether one would help.
4. Check button labels. They should say the outcome. Flag Submit, Click here, and Learn more when a specific label would fit.
5. Check forms: only the fields that are needed, labels, inline errors, and a privacy note near the email field.
6. Check trust: real contact details, and no fake countdown or invented customer count. If a number is in the code with no source, flag it.
7. Confirm a successful form or download has a thank-you state and that the success is tracked without putting the email in the analytics event.
8. On landing pages, flag nav links that pull people away from the primary action before they can take it.
9. Return suggested copy and layout changes, ordered by how likely they are to help. Mark that order as your judgment, not a measured result.

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 P26, for example P26-1, P26-2.)
- 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. Conversion & CTA Audit: what to check Review clarity and the primary action, page by page. Do not rewrite the site in this pass. Suggest copy. Do not invent testimonials or numbers. 1. For each page, state the one primary action in a sentence, then say whether a clear control for it is visible without scrolling, on a wide window and on a 320px window. 2. Say whether the headline and the line under it tell a new visitor what this is, who it is for, and what they get. 3. If there is a sticky mobile bar, say whether it covers content or the keyboard. If a long page has no sticky action, say whether one would help. 4. Check button labels. They should say the outcome. Flag Submit, Click here, and Learn more when a specific label would fit. 5. Check forms: only the fields that are needed, labels, inline errors, and a privacy note near the email field. 6. Check trust: real contact details, and no fake countdown or invented customer count. If a number is in the code with no source, flag it. 7. Confirm a successful form or download has a thank-you state and that the success is tracked without putting the email in the analytics event. 8. On landing pages, flag nav links that pull people away from the primary action before they can take it. 9. Return suggested copy and layout changes, ordered by how likely they are to help. Mark that order as your judgment, not a measured result. 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 P26, for example P26-1, P26-2.) - 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.