This is a heavyweight PR review system that runs five parallel analysis passes with shuffled diffs to reduce ordering bias, then uses majority voting to filter findings. A separate Claude Opus instance validates results without seeing the original passes. It posts inline GitHub comments and can generate autofix commits with test validation and scope checks. The interesting part is the learning loop: after PRs merge, you run a resolve command to classify whether findings were actually fixed, then the system adjusts category weights to suppress noisy issue types over time. Requires gh CLI and assumes you want a thorough, opinionated review process rather than a quick scan. Overkill for small changes, but if you're serious about catching bugs in high-stakes PRs and willing to let it learn from your merge decisions, it's built for that.
npx skills add https://github.com/pproenca/dot-skills --skill bug-review