Design or write reproducible tests matched to behavioral risk before implementation. Use for product behavior and for engineering tooling and infrastructure only when native checks are insufficient and concrete complexity or failure risk warrants proportionate dedicated tests.
Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.
Edit or rewrite human-readable technical prose for clarity while preserving meaning and precision. Use for comments, docstrings, documentation, commit or pull request text, issues, reports, runbooks, logs, errors, command help, and similar writing rather than factual, structural, or marketing review.
Verify graphical browser, desktop, or Electron behavior through the actual interface. Use when screenshot, accessibility, console, network, trace, or browser-driven evidence is required; exclude terminal-hosted interfaces.