Code Reviewer
What it does
Get high-quality, technical feedback on your source code before it hits production or a formal PR review. This skill analyzes your logic, identifies potential bugs, and suggests architectural improvements based on industry best practices for the specific language you are using. Instead of just pointing out errors, it provides the "why" behind every suggestion, helping you understand the underlying design patterns or performance bottlenecks. It is particularly useful when you are working in a new language, refactoring legacy code, or looking for a second pair of eyes to ensure your implementation is idiomatic and maintainable.Use cases
- Pre-PR Polish: Run your local changes through the reviewer to catch "nitpicks" and logic gaps before submitting a Pull Request to your team.
- Language Migration: Paste code written in a language you're learning to see if you're using the correct idioms or if you're writing "Java code in Python."
- Performance Tuning: Submit a complex method that feels slow to identify algorithmic inefficiencies or memory leaks.
- Refactoring Legacy Code: Provide an old function to find a more modern, concise way to implement the same logic using updated language features.
How to use
Provide the name of the programming language followed by the code block, method, or file you want analyzed. For the best results, include a brief sentence about the intended goal of the code.markdown
I want you to act as a Code reviewer who is experienced developer in the given code language. I will provide you with the code block or methods or code file along with the code language name, and I would like you to review the code and share the feedback, suggestions and alternative recommended approaches. Please write explanations behind the feedback or suggestions or alternative approaches.Tips
- Provide Context: Tell the AI if the code is for a high-traffic production environment or a quick prototype; the review criteria for performance and scalability will change accordingly.
- Request Specific Focus: If you are only worried about security or readability, specify that in your request (e.g., "Review this for potential SQL injection vulnerabilities").
- Iterate on Suggestions: When the AI suggests an alternative approach, ask it to implement that alternative as a code block so you can compare the two versions side-by-side.
- Include Dependencies: If your code relies on specific libraries or frameworks, mention them so the reviewer doesn't suggest a native solution that conflicts with your stack.
Notes
- Lack of Runtime Context: The AI cannot execute the code, so it may occasionally miss bugs that only appear during runtime or under specific environment configurations.
- Scope Limitations: For very large files, the AI may lose track of global variables or dependencies defined outside the provided snippet.