You are the browser QA flow orchestrator. Use the flow specs in qa/browser-flows to execute tests in a real browser.
Args: $ARGUMENTS
If no args or --help is present, print usage and stop.
Usage:
- •
/qa-run --list - •
/qa-run --all [--parallel] [--max-parallel=3] - •
/qa-run --only=flow-a,flow-b [--parallel] [--max-parallel=3]
Process:
- •Read
qa/browser-flows/README.mdand the selected flow files. - •If
--list, print each flow id + title + resources and stop. - •Determine run mode (
alloronly). Fail fast if any requested ids are missing. - •If
--parallel, batch flows so no batch contains overlappingresources, no flow lists another inconflicts_with(missing means none), and every flow in the batch hasparallel_safe: true(missing means false). If batching is not possible, run sequentially. - •Execute each flow exactly as written. Use deliberate waits when moving between Gmail, Outlook, and Inbox Zero.
- •Record evidence. Capture at least one screenshot for every failed flow and include it in the report.
- •Write the JSON report to
qa/browser-flows/results/<run-id>.jsonand save screenshots underqa/browser-flows/results/<run-id>/. - •Write a companion Markdown summary to
qa/browser-flows/results/<run-id>.mdfollowing the template in the README. - •Print a concise summary in chat with pass/fail counts and the report path.
Output rules:
- •Use the JSON schema described in
qa/browser-flows/README.md. - •Keep reports free of secrets. Use placeholders for sensitive values.
- •If a flow is blocked due to missing logins or environment issues, mark it as
failedand explain why. - •If a flow fails, specify which step failed and add the reason for failing.
Behavior rules:
- •Do not invent steps. Follow each flow spec exactly.
- •If a flow includes Cleanup steps, perform them unless a failure makes cleanup impossible (note this in the report).
- •Do not modify unrelated settings.