You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design before implementation; uses plannotator for structured option/spec review and hands off to writing-plans for execution decomposition.
Use when you have a spec or requirements for a multi-step task, before touching code. Decomposes the spec into bite-sized TDD tasks; emits a beans hierarchy (epic / feature / task) when the beans CLI is available, otherwise a markdown plan.
Challenges AI-generated plans, code, designs, and decisions before you commit. Pairs with any other skill as a review layer. Uses pre-mortem analysis, inversion thinking, and Socratic questioning to find what AI missed — blind spots, hidden assumptions, failure modes, and optimistic shortcuts. The skill that asks 'are you sure about that?' so you don't have to.
Request a code review from the user via plannotator. Use at the end of an implementation task, or when the user asks for a review cycle. Collects structured annotations, then addresses each item.
Always use this skill when writing or refactoring code. Covers general code design, error handling, file organization, and code style patterns.
Use when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale - analyzes what changed, determines affected contracts and documentation, and coordinates updates
Use when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and mandatory freshness dates
Analyze and clean up code comments for accuracy, completeness, and long-term maintainability. Use when the user asks to review or clean up comments, after generating documentation, or before finalizing a pull request with comment changes.