Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Initial release of critical-code-reviewer — a ruthlessly high-standard adversarial code review skill. - Detects security flaws, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. - Flags issues in error handling, type safety, performance, accessibility, and code quality with structured severity tiers (Blocking, Required, Suggestions, Noted). - Implements explicit detection for typical sloppiness, structural problems, language-specific red flags, and incomplete solutions. - Provides direct, actionable, and constructively brutal feedback, with the option to group and discuss issues or post reviews as PR comments. - Clearly explains boundaries when context is missing and calibrates severity and recommendations accordingly.