Analyze any codebase and generate a complete .claude/ configuration to make it AI-native. Use when setting up Claude Code for a new or existing repo. Handles cold-start by detecting stack, framework, patterns, and generating tailored CLAUDE.md, agents, skills, rules, and hooks.
Validate your .claude/ configuration. Checks that commands work, paths exist, hooks are valid, and agents are well-formed. Use after /claude-init or /update to catch issues.
Land completed work — verify tests, present options (merge/PR/keep/discard), execute chosen workflow. Auto-triggered after implementation and review pass. Also available as /finish.
Two-stage code review: spec compliance first, then code quality. Auto-triggered after implementation. Also available as /review.
Execute implementation plans using fresh subagents per task with two-stage review. Auto-triggered for plans with multiple independent tasks. Also available as /subagent-dev.
Verification before completion — no success claims without fresh evidence. Auto-triggered before any completion claim. Also available as /verify.
Re-analyze a repo and update its existing .claude/ configuration. Detects stack changes, new dependencies, and config drift without overwriting customizations. Use when the codebase has evolved since initial /claude-init.
Turn vague requests into structured, testable specs through collaborative design. Auto-triggered when requirements are ambiguous. Explores intent, constraints, and alternatives before implementation. Also available as /clarify.