Browser QA Audit
Exercise a running app in a real browser, triage what breaks, and produce a report-only QA findings list with a health score — no code changes.
How it runs
| # | Step | Who runs it | What happens |
|---|---|---|---|
| 1 | Plan observable coverage | Researcher | Confirm the target and turn user intent into bounded journeys, states, and evidence requirements. |
| 2 | Exercise the application | Developer | Run the planned journeys in a real browser and capture reproducible, redacted evidence. |
| 3 | Write the QA report | Developer | Triage observed defects, compute the health score, and provide owners with exact reproduction evidence. |
| 4 | Evaluate the deliverable | Reviewer | Independently grade the observable deliverable and route it to finish, repair, or user escalation. |
| 5 | Repair the deliverable | Developer | Fix only the concrete gaps from the latest independent review. |
| 6 | Finish | Developer | All deterministic and reviewer criteria passed. |
| 7 | Escalate unresolved concerns | Developer | The bounded repair loop ended without a defensible pass. |
Say something like "qa report only" or "just report bugs" or "test but dont fix" in chat to start it.
Needs toolsets: @playwright/mcp.