This project is a specialized instruction set for AI coding agents designed to perform structured, language-specific code reviews. It functions as an automated tool that evaluates source code against predefined checklists to identify security, performance, and architectural inconsistencies across diverse technology stacks.
The system distinguishes itself by employing a multi-phase analysis pipeline that moves from high-level architectural assessments to granular, line-by-line inspections. It utilizes a severity-based taxonomy to categorize findings, clearly separating blocking security issues from optional stylistic improvements to provide actionable, consistent feedback for developers.
Beyond core analysis, the framework standardizes the review process by applying context-aware documentation and language-specific guidelines. It incorporates collaborative techniques to improve communication between developers, ensuring that feedback is delivered in a structured, template-driven format that reduces friction and supports team-wide code quality standards.
