What problem does it solve? Catching structural bugs before code lands is hard: SQL injection, race conditions, unvalidated LLM output, and incomplete enum handling slip through manual review. This Skill automates a pre-landing review of your branch diff so critical issues are found and often fixed before merge. ## Core Features & Use Cases - Two-pass diff analysis: Runs a CRITICAL pass (SQL safety, race conditions, LLM trust boundaries, shell injection, enum completeness) followed by an INFORMATIONAL pass (async mixing, type coercion, CI/CD pipeline issues). - Parallel specialist subagents: Dispatches dedicated reviewers for testing gaps, maintainability, security, performance, data migrations, API contracts, and adversarial red-team analysis on large diffs. - Fix-First workflow: Mechanical fixes (dead code, N+1 queries, magic numbers) are applied automatically, while judgment calls are batched into a single structured decision question. - Greptile triage: Fetches, classifies, and replies to Greptile bot comments on GitHub PRs with evidence-backed responses. - Use Case: Before merging a feature branch, ask for a review and get a report of critical and informational issues with auto-applied fixes, plus design checklist findings when frontend files changed. ## Quick Start Ask the assistant to review this PR against the base branch before merging.