What problem does it solve? When receiving code review feedback, AI assistants often respond with sycophantic agreement or blindly implement suggestions without verifying them against the actual codebase, leading to broken functionality, unnecessary features, and misunderstood requirements. ## Core Features & Use Cases - Verify Before Implementing: Enforces a read-understand-verify-evaluate-respond workflow so feedback is checked against the actual codebase before any changes are made. - Source-Based Handling: Distinguishes between trusted partner feedback and external reviewer feedback, applying extra scrutiny and YAGNI checks to external suggestions. - Structured Pushback: Provides concrete guidance on when and how to disagree with reviewers using technical reasoning, including a graceful path for correcting your own rebuttals when wrong. - Use Case: A reviewer asks you to delete legacy code and implement six fixes. Instead of agreeing immediately, you grep the codebase, discover the legacy code is needed for backward compatibility, clarify the two ambiguous items, then implement the verified fixes one at a time with tests. ## Quick Start Apply the receiving-code-review skill to evaluate and respond to the review comments on my pull request before making any changes.
