This implements a proper multi-agent review system where three specialized judges (Requirements Validator, Solution Architect, Code Quality Reviewer) independently critique your work, then debate their findings to reach consensus. Each judge uses chain-of-verification to check their own reasoning before reporting. It's designed for completed work review, not real-time fixes. You point it at recent changes, a specific commit, or conversation context, and it comes back with scored assessments, identified gaps, alternative approaches, and refactoring opportunities. Honestly, it's overkill for quick changes but genuinely useful when you want to catch blind spots before shipping something significant or need structured feedback on architectural decisions.
npx skills add https://github.com/neolabhq/context-engineering-kit --skill critique