This skill enables developers to perform AI-powered code reviews, identifying bugs, security vulnerabilities, and quality risks in their code. It can operate autonomously or be triggered explicitly, making it suitable for developers looking to enhance code quality and security.
$ npx skills add https://github.com/coderabbitai/skills --skill code-reviewCodeRabbit Code Review is an agent-native skill that integrates AI-powered code analysis into your coding workflow. It automatically detects bugs, security vulnerabilities, and quality risks in your code before you merge. The skill works across 35+ coding agents including Claude Code, Cursor, GitHub Copilot, and others, operating either autonomously or when explicitly triggered. Simply ask your agent to review your code, and it will analyze your changes, group findings by severity, and optionally fix issues and re-review. Installation requires the CodeRabbit CLI and takes minutes to set up globally or per-project.
Install the skill using npx and trigger reviews as needed.
Identify bugs and security vulnerabilities in code changes
Group findings by severity for better prioritization
Conduct code reviews on staged or committed changes
Autonomously fix issues and re-run reviews to verify
$ npx skills add https://github.com/coderabbitai/skills --skill code-reviewgit clone https://github.com/coderabbitai/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Check the GitHub repository or documentation for usage examples.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan