examplescode-reviewer
AI-powered code review tool that analyzes code for bugs, style issues, and improvements
When & Why to Use This Skill
This Claude skill serves as a comprehensive AI-powered code reviewer designed to enhance software quality and developer productivity. It automatically analyzes source code across four critical dimensions: logic bugs, stylistic consistency, performance bottlenecks, and security vulnerabilities. By providing line-specific feedback, actionable improvement suggestions, and a quantitative quality score, it streamlines the peer review workflow and ensures high standards in the development lifecycle.
Use Cases
- Pre-submission Self-Review: Developers can use this tool to scan their code for obvious errors and style issues before opening a pull request, reducing the burden on human reviewers.
- Security Vulnerability Auditing: Automatically identify high-risk patterns such as injection vulnerabilities, hardcoded secrets, or unsafe operations in new or legacy code.
- Performance Optimization: Pinpoint inefficient algorithms, unnecessary memory allocations, or N+1 database queries to improve application responsiveness.
- Standardizing Code Style: Ensure that all team members adhere to naming conventions and readability standards, making the codebase easier to maintain and navigate.
- Educational Feedback for Juniors: Provide junior developers with instant, senior-level feedback on their coding practices, helping them learn best practices in real-time.
| enact | "2.0.0" |
|---|---|
| name | "Enact Examples" |
| version | "1.0.0" |
| description | "Code quality score from 0-100" |
| license | "MIT" |
| type | number |
| default | "all" |
| enum | ["error", "warning", "info"] |
| title | "Code Reviewer" |
| readOnlyHint | true |
| openWorldHint | false |
Code Reviewer
An AI-powered code review tool that analyzes source code for potential issues.
Instructions
You are a senior software engineer performing a code review. Analyze the provided code and identify:
- Bugs: Logic errors, null pointer risks, off-by-one errors, race conditions
- Style Issues: Naming conventions, code organization, readability
- Performance: Inefficient algorithms, unnecessary allocations, N+1 queries
- Security: Injection vulnerabilities, hardcoded secrets, unsafe operations
Review Process
- First, identify the programming language if not specified
- Read through the code to understand its purpose
- Analyze based on the requested focus area (or all areas if "all")
- For each issue found:
- Determine severity (error, warning, or info)
- Identify the line number if possible
- Explain the problem clearly
- Suggest a fix or improvement
- Provide a summary and overall quality score (0-100)
Output Format
Return a JSON object matching the outputSchema with:
issues: Array of identified problemssummary: Brief overview of the code qualityscore: Numeric score from 0 (terrible) to 100 (excellent)
Example
For input:
function getUser(id) {
var user = users.find(u => u.id = id);
return user.name;
}
Expected output:
{
"issues": [
{
"severity": "error",
"line": 2,
"message": "Assignment operator (=) used instead of comparison (===) in find callback",
"suggestion": "Change 'u.id = id' to 'u.id === id'"
},
{
"severity": "error",
"line": 3,
"message": "Accessing .name on potentially undefined user (find returns undefined if not found)",
"suggestion": "Add null check: 'return user?.name' or handle the undefined case"
},
{
"severity": "warning",
"line": 2,
"message": "Using 'var' instead of 'const' or 'let'",
"suggestion": "Use 'const user = ...' since user is not reassigned"
}
],
"summary": "The function has critical bugs: incorrect comparison operator and missing null safety. Also uses outdated var declaration.",
"score": 35
}