Performance Testing Review Multi Agent Review

This is a framework for orchestrating multiple specialized AI agents to review code from different angles at once. You spin up security auditors, architecture specialists, performance analysts, and other domain experts in parallel or sequence, then synthesize their findings into a unified report with conflict resolution. The source includes actual routing logic, context propagation patterns, and a hybrid execution model. It's ambitious and the coordination overhead is real, but if you're doing serious code reviews at scale and want multiple expert perspectives without the manual effort of running separate tools, this gives you the scaffolding. Best suited for complex codebases where single-perspective reviews miss critical issues across domains.

Install to Claude Code

npx -y skills add sickn33/antigravity-awesome-skills --skill performance-testing-review-multi-agent-review --agent claude-code