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.

skills.sh installs: 263
GitHub stars: 39.4K
last updated: Jun 3, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Compatibility and maintenance

Compatibility alias of error-debugging-multi-agent-review; use that ID for new references when no existing contract requires this one. The full instructions and support files remain local so existing installations continue to work offline. This is one shared procedure, not an additional capability. Preserve the callable ID when an existing manifest or client configuration uses it. Modified in AAS on 2026-09-05; original metadata and license notices are retained.

Coordinate a bounded code review

When to Use

Review a defined diff or subsystem from several relevant perspectives, such as correctness, authorization and performance. The skill describes a review procedure; it does not install an orchestration engine or prove compliance.

SKILL.md on GitHub