Multi-agent code review system for uncommitted changes with 6 specialized reviewer roles (security, bug, quality, contract, testing, history), confidence scoring and false positive filtering

Multi-agent PR review system with specialized reviewers, inline comments, and automatic PR description generation using GitHub CLI

Test any Claude skill using RED-GREEN-REFACTOR cycle with subagent pressure testing to verify the skill resists agent rationalization and bypass attempts

Universal prompt testing methodology using RED-GREEN-REFACTOR cycle with subagents, supporting A/B testing and regression testing for commands, hooks, skills, and production prompts