Quality

Caveman Optimize turns Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation. Use when a Claude Code session needs to inspect an optimization observation, evaluate a candidate change, or act on the current Caveman optimization report.

Caveman Review generates ultra-compressed code review comments that cut noise from PR feedback while preserving actionable signal. Use it when reviewing pull requests or diffs.

Investigate First diagnoses ambiguous failures before editing code. Use it when the cause is unknown, behavior is intermittent, or you need evidence-ranked hypotheses before changing product code.

Safe Refactor restructures code while preserving behavior. Use it for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

Surgical Patch fixes bugs and small behavior changes at the narrowest responsible layer. Use Surgical Patch when regression proof, preserved surrounding behavior, and task-relevant tests matter.

Verify and Stop proves existing work meets acceptance conditions without expanding scope. Use it for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Babysit PR monitors a pull request and its review cycle until it is ready to merge, checking review comments, unresolved threads, and CI status, and fixing actionable issues. Use when asked to babysit, monitor, or keep checking PRs until all actionable issues are resolved.

Debugging and Error Recovery guides systematic root-cause debugging when tests fail, builds break, behavior doesn't match expectations, or any unexpected error occurs. Use it to follow a structured triage process to find and fix the root cause rather than guessing.

Doubt-Driven Development subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, in unfamiliar code, or when stakes are high.

Incremental Implementation breaks multi-file changes into small vertical slices, each implemented, tested, and verified before moving on. Use it when a task feels too large to land in one step or when implementing any feature touching multiple files.

Performance Optimization measures bottlenecks and optimizes frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect regressions, when Core Web Vitals need improvement, or when profiling reveals bottlenecks.

Security and Hardening hardens code against vulnerabilities. Use it when handling user input, authentication, data storage, or external integrations, and when building features that accept untrusted data, manage user sessions, or interact with third-party services.