What problem does it solve? Single-model code reviews miss defects and reflect one model's biases. This Skill runs a multi-LLM review pipeline that synthesizes perspectives from several AI providers, detects security vulnerabilities and incomplete implementations, and posts findings directly to pull requests. ## Core Features & Use Cases - Multi-Provider Review Pipeline: Orchestrates parallel reviews across external AI providers (Codex, Copilot, Qwen, and others) with a 75% consensus gate before delivering findings. - Security and Quality Analysis: Detects OWASP vulnerabilities, performance issues, architecture problems, and autonomous-codegen risk patterns like placeholder logic and dead branches. - Stub Detection and PR Integration: Scans changed files for TODO markers, empty functions, and mock data in production paths, then posts the review synthesis as a GitHub PR comment via the gh CLI. - Use Case: Before merging a PR with authentication changes, invoke the review to get multi-model security findings, TDD evidence assessment, and implementation completeness verification posted directly to the PR. ## Quick Start Ask the AI to review the current pull request for security issues and code quality using the multi-provider code review pipeline.
