Make a fixture from a sanitized log
Cursor handles this as a draft: Replace emails with placeholders. Do not use production data.
- Steps
- 4
- Cost
- low
- Time
- Half an hour
Unverified · cursor.com · 16 Oct 2026
Loading the catalog…
Loading the catalog…
Cursor Agent walks one screen for missing names, keyboard traps, and contrast notes, then patches the clear code issues.
A marketing site plus the app is not one pass. Name the path.
Ask it to search for the route's components before editing.
The agent will miss things a keyboard pass catches, and it may 'fix' a control your design system already names.
The prompt keeps visual redesign out of the diff.
These are editorial labels so you can compare playbooks. They are not measurements.
No. Status is unverified. Paste the prompt, keep the version that worked, and do not treat the time or cost lines as measurements.
It catches a class of code bugs on one screen. It is not an audit and it does not certify conformance.
Official documentation URL, checked when this seed was written. The prompt and steps are an original AI Playbook Gems playbook, not a quotation of a customer story, and have not been re-run.
Machine-readable copy: JSON
Cursor handles this as a draft: Replace emails with placeholders. Do not use production data.
Unverified · cursor.com · 16 Oct 2026
Cursor handles this as a draft: The smallest change that could explain the failure I paste. Do not commit.
Unverified · cursor.com · 15 Oct 2026
Cursor's agent searches the repo, edits the files for one ticket, and runs the checks you name. The ticket's out-of-scope list is part of the prompt.
Unverified · cursor.com · 15 Oct 2026