--- description: Run Playwright E2E tests (full suite…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Run Playwright E2E tests (full suite or filtered) argument-hint: [optional grep-pattern] allowed-tools: Bash(pnpm test\:e2e: ), Bash(pnpm dev: ) --- Run the Playwright E2E suite for: $ARGUMENTS (omit for full suite). ## Steps 1. If $ARGUMENTS is empty, run pnpm test:e2e . Otherwise run pnpm test:e2e -- --grep "$ARGUMENTS" . 2. Playwright needs the dev/preview server. The config is expected to handle webServer setup automatically, if it fails complaining about a server, surface the message and ask the user to start pnpm dev first. 3. On success, print a 1-line summary: <N> e2e tests passed in <duration> . 4. On failure: - Print the failed spec names and the first failing assertion's stack trace. - Mention pnpm test:e2e:ui and pnpm test:e2e:report for interactive debugging. - Do not auto-retry unless the user asks. ## Tips - Run a single file: /e2e contact-validation - Run with UI: ask the user to run pnpm test:e2e:ui directly (interactive, not suitable for this command
claude-code
More testing loops
Ship the release
Run tests and update changelog until both pass without altering the public API.
/goal ship the release --success "tests pass and changelog updated" --constraints "do not touch the public API" --mode ordered
testingmedium risk
/ralph-loop "fix all tests" --max-iterations 5 (iterates until…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
/ralph-loop "fix all tests" --max-iterations 5 (iterates until passing
testingmedium risk
Trim what loads before first paint
Reduce the data downloaded before the first screen appears, with tests and screenshots guarding behavior and appearance.
Reduce the data [web app] downloads before its first screen appears. First record passing tests, mobile and desktop screenshots, and compressed transferred bytes—the data actually downloaded. Use the build report only to suggest candidates. Defer, compress, or remove one item, then rebuild and rerun every check. Keep it only if tests pass, screenshots are pixel-identical, and bytes decrease; otherwise revert. Stop when no safe candidate remains, progress stalls, or approval is needed. Return measurements, changes, and untested states.
testingmedium risk