review▌

Multi-perspective code review with parallel specialists.

Review PyTorch pull requests focusing on what CI cannot check: code quality, test coverage adequacy, security vulnerabilities, and backward compatibility.

Use this skill when the user gives a product name and asks for an end-to-end documentation/API quality review.

Provide a systematic checklist for conducting thorough code reviews. This skill helps reviewers ensure code quality, catch bugs, identify security issues, and maintain consistency across the codebase.

TypeScript/JavaScript Code Review Skill \n @./../_shared/typescript-commands.md \n Code Review Guidelines \n Review pull requests with a focus on: \n \n Readability and maintainability \n Appropriate test coverage \n Compliance with project coding standards and conventions \n Code quality and best practices \n Type safety and proper TypeScript usage \n React best practices (when applicable) \n

This guide explains how to add line-specific review comments to pull requests using the GitHub CLI (gh) API or mcp__github_inline_comment__create_inline_comment if it not available, similar to how the GitHub UI allows commenting on specific lines of code.

These patterns are intentional and correct - do not report as issues:

This skill ensures all code follows security best practices and identifies potential vulnerabilities.

Find access control vulnerabilities by investigating how the codebase answers one question:

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.