What problem does it solve? Manual code reviews are slow, inconsistent, and often miss security, performance, or architecture issues. This Skill automates comprehensive pull request reviews by deploying specialized review agents that analyze code in parallel and post structured feedback directly to GitHub. ## Core Features & Use Cases - Multi-Agent Review System: Deploys specialized agents for security, performance, architecture, style, and accessibility analysis on a single PR. - PR-Based Swarm Management: Creates review swarms from PR data, auto-assigns agents based on labels, and selects topology by PR size. - Quality Gates & Automation: Enforces merge-blocking thresholds, integrates with GitHub Actions CI/CD, and supports comment commands like /swarm review. - Use Case: When a developer opens a PR touching authentication code, the Skill automatically spawns security and architecture agents, posts inline review comments, requests changes on critical findings, and adds labels like security-review. ## Quick Start Ask the AI to initialize a multi-agent review for pull request 123 with security, performance, and style agents, then post the findings as a PR review comment.