Performs automated code reviews and quality analysis.

Install

mkdir -p .claude/skills/review-s && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16546" && unzip -o skill.zip -d .claude/skills/review-s && rm skill.zip

Installs to .claude/skills/review-s

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Review code for quality, bugs, and improvements. Use when user wants to review code with /review-s.
99 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Identify logic errors and incorrect calculations
  • Detect input validation gaps and SQL injection risks
  • Find N+1 query problems and inefficient algorithms
  • Assess unclear naming conventions and overly complex functions
  • Provide structured feedback on code quality

How it works

The skill gathers code from a specified file or git diff, analyzes it for bugs, security, performance, and readability, then documents findings in a structured markdown format.

Inputs & outputs

You give it
Optional file path to review or current git diff
You get back
Structured markdown feedback on code quality, bugs, and improvements

When to use review-s

  • Reviewing code diffs
  • Identifying security vulnerabilities
  • Improving code performance

About this skill

Review Skill (/review-s)

Review code and provide structured feedback on quality, bugs, and improvements.

Input

  • $ARGUMENTS: Optional file path to review
  • If no path provided, review current git diff

Review Focus Areas

1. Bugs & Errors

  • Logic errors and incorrect calculations
  • Missing null/None checks
  • Unhandled edge cases
  • Incorrect exception handling

2. Security

  • Input validation gaps
  • SQL injection risks
  • Sensitive data exposure
  • Authentication/authorization issues

3. Performance

  • N+1 query problems
  • Missing database indexes
  • Inefficient loops or algorithms
  • Unnecessary memory allocations

4. Readability

  • Unclear naming conventions
  • Overly complex functions
  • Missing or unclear comments
  • Inconsistent code style

Process

Step 1: Gather Code

If file path provided:

  • Read the file directly

If no path:

  • Run git diff to see unstaged changes
  • Run git diff --staged to see staged changes

Step 2: Analyze Code

For each file:

  1. Check for bugs and logic errors
  2. Look for security vulnerabilities
  3. Identify performance issues
  4. Assess readability and maintainability

Step 3: Document Findings

Structure feedback by severity.

Output Format

## Code Review

### Summary
[One sentence overall assessment]

### Issues Found

#### Critical (Must Fix)
- [issue]: [location] - [brief explanation]

#### Warnings (Should Fix)
- [issue]: [location] - [brief explanation]

#### Suggestions (Nice to Have)
- [suggestion]: [location] - [brief explanation]

### What's Good
- [positive observation]

Guidelines

  • Be specific about locations (file:line if possible)
  • Provide actionable feedback with clear remediation steps
  • Don't nitpick style unless it significantly impacts readability
  • Acknowledge good patterns and well-written code
  • Focus on issues that could cause bugs, security issues, or maintenance problems

When not to use it

  • When the user does not want to review code
  • When the user does not explicitly use `/review-s`
  • When the task is not related to code quality, bugs, or improvements

Limitations

  • Requires explicit user request for code review
  • Focuses on specific review areas (Bugs, Security, Performance, Readability)
  • Does not nitpick style unless it impacts readability

How it compares

This skill provides a systematic and structured approach to code review, focusing on specific areas like security and performance, which offers a more thorough analysis than a casual manual review.

Compared to similar skills

review-s side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
review-s (this skill)03moNo flagsIntermediate
find-bugs57moNo flagsIntermediate
tech-debt-analyzer59moReviewIntermediate
static-analysis56moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

find-bugs

davila7

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

529

tech-debt-analyzer

ailabs-393

This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use this for identifying code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and creating comprehensive technical debt documentation.

522

static-analysis

gmh5225

Expertise in LLVM-based static analysis including dataflow analysis, pointer analysis, taint tracking, and program verification. Use this skill when implementing security scanners, bug finders, code quality tools, or performing program analysis research.

518

agent-code-analyzer

ruvnet

Agent skill for code-analyzer - invoke with $agent-code-analyzer

317

codex-code-review

tyrchen

Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.

16

review-code

catlog22

Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".

22

Search skills

Search the agent skills registry