--- description: Pre-PR quality gate, then open a…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Pre-PR quality gate, then open a PR to develop. allowed-tools: Bash(turbo run ), Bash(pnpm format:check), Bash(pnpm test), Bash(pnpm codegen), Bash(git ), Bash(gh ) --- Run the quality gate and ship. Stop and report at the first failing step. 1. turbo run lint:staged — lint changed files (fix issues). 2. pnpm format:check — Prettier must be clean ( pnpm format to fix). 3. pnpm test — Vitest must pass. 4. pnpm codegen — if anything changed, generated types were out of sync; commit them. 5. Commit using Conventional Commits ( feat: / fix: / chore: / docs: …) on a feature branch (never commit straight to develop ). 6. Push with git push -u origin <branch> and open a PR targeting develop via gh (only when the user asked to open a PR). Branch flow: feature → develop → staging (QA) → main (prod
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