What problem does it solve?
This Skill eliminates the risk of committing code with undetected security vulnerabilities, logic errors, or test regressions that manual review often misses, ensuring only verified, high-quality code enters the repository.
Core Features & Use Cases
- Static Security Scanning: Automatically detects hardcoded secrets, injection flaws, unsafe eval/exec calls, and other high-risk patterns in added code lines.
- Baseline-Aware Quality Gates: Only flags new test failures or lint errors introduced by your changes, ignoring pre-existing issues in the codebase.
- Independent Code Review: Uses a separate subagent with no context of your implementation to catch issues you might have overlooked, with fail-closed rules for security and logic errors.
- Auto-Fix Loop: Automatically resolves reported security and logic issues with up to two fix-and-reverify cycles, reducing manual remediation work.
Use case: A developer finishing a bug fix can run this skill before committing to catch any overlooked security risks or regressions without waiting for a human reviewer.
Quick Start
Use the requesting-code-review skill to verify your recent code changes before committing them to the git repository.