Claude-skill-registry code-reviewer

Provides comprehensive code review feedback based on best practices, style guides, and potential bug detection. Use when the user requests a code review, asks for improvements to code, or needs to ensure code quality.

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/general-productivity" ~/.claude/skills/majiayu000-claude-skill-registry-code-reviewer-5c185b && rm -rf "$T"

manifest: skills/data/general-productivity/SKILL.md

Code Review Skill

This skill helps to perform thorough code reviews, focusing on readability, maintainability, performance, security, and adherence to project-specific coding standards.

When to Use This Skill

When a user explicitly asks for a "code review" of a file or set of files.
When a user asks to "improve the quality" or "refactor" a piece of code.
When a user submits code and asks for "feedback" or "suggestions".

Core Capabilities

Syntax and Style Check: Verify adherence to established coding standards (e.g., PEP 8 for Python, ESLint rules for JavaScript).
Best Practices: Identify deviations from common best practices for the given language/framework.
Potential Bugs/Errors: Highlight common pitfalls, edge cases, or logical errors.
Performance Optimization: Suggest areas where code could be made more efficient.
Security Vulnerabilities: Point out potential security risks.
Readability and Maintainability: Provide feedback on code clarity, comments, variable naming, and overall structure.
Testability: Assess if the code is easily testable and suggest improvements.

Workflow

Identify Scope: Determine which files or code snippets are part of the review request.
Read Code: Use
```
read_file
```
to access the content of the specified files.
Analyze:
- Apply language-specific linting/static analysis tools if available (e.g.,
```
pylint
```
  ,
```
flake8
```
  ,
```
eslint
```
  ).
- Perform a semantic analysis based on the description and context.
- Cross-reference with project-specific style guides or documentation if linked in
```
references/
```
  .
Generate Feedback:
- Structure feedback clearly, categorizing by type (e.g., "Style", "Potential Bug", "Suggestion").
- Provide specific line numbers or code snippets for each piece of feedback.
- Explain why a change is suggested and, if possible, offer a concrete example of how to fix it.
- Prioritize critical issues (bugs, security) over stylistic suggestions.
Present Review: Output the comprehensive review to the user.

Example Usage

User Prompt: "Please review

src/main.py

for any issues."

Agent Action:

```
read_file("src/main.py")
```
Run
```
pylint src/main.py
```
(if configured).
Analyze code content.
Generate a markdown-formatted review with findings.