What problem does it solve?
This Skill helps teams reduce review cycles and improve code quality by coordinating AI agents to analyze pull requests for security, performance, style, architecture, and accessibility concerns.
Core Features & Use Cases
- Multi-agent PR reviews: Runs specialized review agents across key quality dimensions to produce comprehensive feedback and consistent standards.
- PR management automation: Initializes swarm reviews from PR context, posts review progress/results, and supports quality-gate enforcement for merge readiness.
- Targeted checks with guardrails: Performs security-focused validation (e.g., secrets, permissions, injection risks) and applies threshold-based actions such as requesting changes for critical issues.
Use case: When a contributor opens a PR that touches authentication or database logic, use the swarm review to surface high-risk security issues, performance regressions, and architectural violations early—then block or warn based on severity thresholds.
Quick Start
Run a comprehensive multi-agent review for pull request 123 with security, performance, style, architecture, and accessibility agents using your GitHub CLI context.