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.

Split work into non-overlapping parallel streams, track each, and merge without conflicts. Use when multiple agents/threads work on one repo simultaneously.

Name functions, variables, and classes for intent and keep each unit single-responsibility. Use when code is hard to read or a function keeps growing.

Detect and eliminate N+1 query patterns in ORM code — find loops that issue one query per row and batch them. Use when list endpoints are slow under load.

Use when writing unit tests that depend on external systems (HTTP, DB, clock, filesystem) — mock at the boundary, never your own internals. Dummy → Stub → Spy → Mock → Fake hierarchy.

Set up a zero-warning lint + format pipeline (ruff/black/prettier/eslint) with auto-fix and CI enforcement. Use to make style a non-issue in any repo.

Use when a bug requires instrumenting code to find it — the log-and-narrow loop: log entry/exit with key vars, tighten the window, repeat, then remove the logs.

Use when resolving git merge conflicts — read conflict markers, understand ours/theirs/base, produce the correct merged result, then re-run tests for logic collisions.

Polish mobile UI with designer judgment — spacing, touch targets, typography, and visual hierarchy — after functional fixes. Use when a mobile view works but looks unfinished.

Use when assessing test coverage — generate reports with pytest-cov, read missing-line output, and prioritize gaps by risk (error paths, auth, money) over raw percentages.