This is a structured PR review system that deploys multiple specialized agents to analyze your code from different angles: security, bugs, code quality, test coverage, API contracts, and historical context. It automatically filters out noise by scoring each finding on confidence and impact, then only posts inline comments that meet your threshold (default is high impact items). The workflow is fairly opinionated, it skips spec and reports folders by default, adds PR descriptions if missing, and won't review draft or closed PRs. The multi-agent approach is thorough but could get expensive on large PRs since it spins up to 6 parallel agents in multiple phases. Best for teams that want systematic reviews with less bikeshedding, though you'll need to tune the impact thresholds to match your tolerance for feedback volume.
npx skills add https://github.com/neolabhq/context-engineering-kit --skill review-pr