What problem does it solve? Manually reviewing code for bugs, security vulnerabilities, and best practices is time-consuming and inconsistent. This Skill automates the review process by running OpenAI Codex CLI in structured fix-and-review cycles, ensuring code meets quality standards before completion. ## Core Features & Use Cases - Automated Review Execution: Runs codex exec commands against files or file groups to detect bugs, security issues, and maintainability problems with line-specific feedback. - Iterative Fix-and-Review Cycles: Applies fixes for identified issues, then re-reviews with targeted prompts to confirm resolution, up to a 2-iteration limit. - Structured Result Analysis: Parses Codex output sections (Bug, Security, Key Issues, Resolved Checks) to determine pass/fail status and decide whether to continue iterating. - Use Case: After implementing a user authentication module, run this Skill to automatically detect issues like missing password hashing or SQL injection, fix them, and verify the fixes through a follow-up review. ## Quick Start Ask the AI to implement your feature and review it with Codex, for example: "Implement user authentication and run it through Codex review."