cleanupSystematic code cleanup after completing features. Use after refactoring or periodically to remove dead code, console statements, TODOs, and tech debt.
code-reviewReview code like a skeptical senior engineer. Use when reviewing PRs, after generating significant code, or before merging changes.
context-managementManage Claude Code sessions effectively. Use during long sessions, multi-step tasks, or when responses start degrading. Covers /clear, checklists, and subagents.
explore-plan-codeStructured workflow for non-trivial tasks. Read files first, create detailed plan, get approval, then implement. Prevents premature coding.
goal-drivenDefine success criteria instead of step-by-step instructions. Enables autonomous LLM iteration toward testable goals.
headless-automationRun Claude Code in CI/CD pipelines, pre-commit hooks, and batch processing. Covers -p flag, fan-out migrations, and pipeline patterns.
multi-claudeRun parallel Claude instances for writer+reviewer patterns, git worktrees, and specialist agents. Use for independent verification and parallel progress.
naive-then-optimizeImplement the obvious correct solution first, then optimize while preserving correctness. Use for algorithms, data transformations, and critical code paths.
simplifyRemove over-engineering and unnecessary abstractions. Use after implementing features or when code feels bloated.
surface-assumptionsIdentify and validate hidden assumptions before they become bugs. Use before implementing features or when reviewing generated code.
test-firstWrite failing tests before implementation. Enables LLM self-correction through feedback loops. Use for new features and bug fixes.
tradeoffsPresent multiple approaches with explicit tradeoffs before committing to one. Use when there are multiple valid solutions to a problem.
visual-iterationUI feedback loop using screenshots. Provide design mock, implement, screenshot result, iterate until matching. Use for visual work.