Review a pull request systematically — correctness, security, tests, docs, and scope — with a concrete checklist. Use when asked to review a PR or as the pre-merge gate.

Review LLM/agent-generated code with extra skepticism — verify claims, check for subtle bugs and invented APIs, and confirm it actually runs. Use for any AI-authored diff before trusting it.

Classify review findings into blocking vs non-blocking (nit) with clear criteria so reviews stay fast and fair. Use when writing or responding to review feedback.

Track code-quality metrics (complexity, length, maintainability) and set failing thresholds so quality doesn't silently decay. Use to put a number on "this is getting too complex".

Use when changing code structure without changing behavior — the mechanical refactoring catalog (extract, rename, inline, move), small-step discipline, tests stay green throughout.

Review your own diff line-by-line before calling work done — read the actual diff, run the checks, and fix your own issues first. Use before reporting any change complete.

Use when modifying code without tests — characterization tests pin current behavior as a golden baseline, find seams for safe injection, and keep edits minimal and localized.

Use when identifying code smells and their fixes — smell→refactor mapping (Long Function→Extract, Primitive Obsession→Value Object, Duplication→Parameterize), with detection signals and worked examples.

Use when reducing codebase complexity — find dead code with vulture/ruff, collapse single-implementation interfaces, inline premature indirection. The 'could the next reader delete this?' test.

Split a large change into small, reviewable, individually-committed diffs so reviewers (human or agent) can follow intent. Use before opening a PR or when a PR is too big to review.