Comprehensive Code Review

VerifiedSafe

Comprehensive code review tool that analyzes code for security vulnerabilities, performance issues, style violations, team conventions, language-specific patterns, dependency freshness, and best practices. Use this skill when reviewing pull requests, specific files, staged changes, or entire codebases to ensure code quality and consistency.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#code-review#security#performance#best-practices#linting

Recommended for

Automated summary

Performs a comprehensive code review covering security, performance, style, team conventions, idiomatic patterns, dependency freshness, and best practices.

Strengths

  • Covers a wide range of review categories (security, performance, style, etc.)
  • Adapts to team conventions by analyzing existing configuration files
  • Checks freshness and security of newly added dependencies
  • Can analyze files, PRs, staged changes, or the entire repository

Limitations

  • Does not execute code, so cannot detect runtime bugs
  • May miss domain-specific defects
  • Dependency freshness check is limited to newly added dependencies
When to use it

Use this skill to get a structured, in-depth review before merging a pull request or after making significant changes.

When not to use it

Avoid using it for non-versioned code or when you need automated test execution or dynamic analysis.

Security analysis

Safe
Quality score88/100

The skill is a template for AI to perform code review, instructing only to read files and use git/GH commands to gather diffs. These are standard, non-destructive operations. There are no instructions for executing harmful commands, exfiltrating data, or disabling security features.

No concerns found

How this analysis is made

Examples

Review staged changes
Review staged changes in my git repository for security and performance issues.
Review a specific file
Review the file src/utils/auth.ts for vulnerabilities and best practices.
Review a pull request
Review PR #42 for style violations and team conventions.

name: code-review description: Performs comprehensive code reviews checking for security vulnerabilities, performance issues, style violations, team conventions, language patterns, dependency freshness, best practices, and code duplication. Use when reviewing code changes, PRs, or files. argument-hint: [file path, PR number, or "staged" for staged changes]

Comprehensive Code Review

Perform a thorough code review of the specified code, checking for security, performance, style, conventions, and best practices.

Input

The target for review is provided as: $ARGUMENTS

Accepted inputs:

  • File path: Review a specific file (e.g., src/utils/auth.ts) or directory containing source files
  • PR number: Review a pull request (e.g., #123 or 123)
  • "staged": Review all currently staged git changes
  • "diff": Review unstaged changes in the working directory
  • "all": All code within the repository
  • No argument: Ask the user what they want reviewed

Review Categories

Analyze the code against each of these categories and report findings:

1. Security Vulnerabilities

Check for:

  • Injection vulnerabilities (SQL, command, XSS, LDAP, etc.)
  • Authentication and authorization flaws
  • Sensitive data exposure (hardcoded secrets, credentials, API keys)
  • Insecure cryptographic practices
  • Missing input validation and sanitization
  • Insecure deserialization
  • Path traversal vulnerabilities
  • CSRF vulnerabilities
  • Improper error handling that leaks information
  • OWASP Top 10 violations

2. Performance Issues

Check for:

  • Inefficient algorithms (O(n²) when O(n) is possible, etc.)
  • N+1 query problems
  • Missing database indexes (when schema is available)
  • Unnecessary re-renders (React, Vue, etc.)
  • Memory leaks and resource cleanup issues
  • Blocking operations in async contexts
  • Excessive memory allocation
  • Missing caching opportunities
  • Inefficient data structures
  • Unoptimized loops and iterations

3. Style Violations

Check for:

  • Inconsistent naming conventions
  • Improper indentation and formatting
  • Missing or excessive whitespace
  • Line length violations
  • Inconsistent brace/bracket style
  • Import ordering issues
  • Commented-out code that should be removed
  • TODO/FIXME comments that need addressing
  • Compliance with project linter rules (if config files exist)

4. Team Conventions

Look for project-specific patterns by examining:

  • Existing code in the repository for established patterns
  • Configuration files (.eslintrc, .prettierrc, pyproject.toml, etc.)
  • Contributing guidelines (CONTRIBUTING.md)
  • Existing documentation
  • Test patterns and naming conventions
  • File and folder organization patterns
  • Error handling patterns used elsewhere in codebase

Flag deviations from established team patterns.

5. Language Canonical Patterns

Check adherence to idiomatic patterns for the source language:

  • TypeScript/JavaScript: Proper typing, async/await usage, module patterns
  • Python: PEP 8, Pythonic idioms, type hints
  • Go: Effective Go guidelines, error handling patterns
  • Rust: Ownership patterns, Result/Option usage
  • Java: Java conventions, design patterns
  • C#: .NET conventions, LINQ usage
  • (Apply similar standards for other languages)

6. Dependency Freshness

When new dependencies are added:

  • Check if the dependency is actively maintained
  • Verify the version is current (not outdated)
  • Look for known vulnerabilities in the version
  • Assess if the dependency is necessary or if native solutions exist
  • Check license compatibility
  • Evaluate the dependency's size and impact on bundle

7. Industry Best Practices

Check for:

  • SOLID principles violations
  • DRY (Don't Repeat Yourself) violations
  • Proper separation of concerns
  • Appropriate error handling and logging
  • Meaningful variable and function names
  • Functions doing one thing well
  • Appropriate abstraction levels
  • Proper use of design patterns
  • Documentation for public APIs
  • Test coverage for new functionality

8. Code Duplication (DRY)

Scan for:

  • Repeated code blocks within the reviewed files
  • Similar logic that exists elsewhere in the codebase
  • Copy-pasted code with minor variations
  • Opportunities to extract common utilities
  • Duplicated algorithms that could be consolidated
  • Repeated patterns that warrant abstraction

Output Format

Structure your review as follows:

# Code Review: [target]

## Summary
[Brief 2-3 sentence overview of the code quality and main findings]

## Critical Issues 🔴
[Security vulnerabilities and bugs that must be fixed]

## Warnings 🟡
[Performance issues, potential bugs, and significant best practice violations]

## Suggestions 🔵
[Style improvements, minor optimizations, and nice-to-haves]

## Detailed Findings

### Security
[Findings or "No issues found"]

### Performance
[Findings or "No issues found"]

### Style
[Findings or "No issues found"]

### Team Conventions
[Findings or "No issues found"]

### Language Patterns
[Findings or "No issues found"]

### Dependencies
[Findings or "N/A - No new dependencies"]

### Best Practices
[Findings or "No issues found"]

### Code Duplication
[Findings or "No duplication detected"]

## Positive Observations ✅
[Note good practices and well-written code sections]

Severity Levels

  • 🔴 Critical: Must fix before merge (security issues, bugs, broken functionality)
  • 🟡 Warning: Should fix (performance, maintainability, potential issues)
  • 🔵 Suggestion: Consider fixing (style, minor improvements)

Instructions

  1. If reviewing a file, read the file first
  2. If reviewing a PR, use gh pr diff [number] to get the changes
  3. If reviewing staged changes, use git diff --cached
  4. If reviewing unstaged changes, use git diff
  5. For context, examine related files in the codebase
  6. Search for duplicated code patterns across the repository
  7. Check for existing linter/formatter configurations
  8. Provide specific line numbers for each finding
  9. Include code snippets showing the issue and suggested fix
  10. Be constructive and educational in feedback

Edge Cases

  • Binary files: Skip with note that binary files cannot be reviewed
  • Generated files: Note if file appears generated and skip detailed review
  • Empty diff: Report that there are no changes to review
  • Invalid file path: Ask user to provide a valid path
  • PR not found: Report error and ask for correct PR number

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/comprehensive-code-review-mmbizked/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/comprehensive-code-review-mmbizked' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/comprehensive-code-review-mmbizked/download' --output '.skill-downloads/comprehensive-code-review-mmbizked/SKILL.md.part' && mv '.skill-downloads/comprehensive-code-review-mmbizked/SKILL.md.part' '.skill-downloads/comprehensive-code-review-mmbizked/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/comprehensive-code-review-mmbizked/SKILL.md' && test -s '.skill-downloads/comprehensive-code-review-mmbizked/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/code-review' && cp -R '.skill-downloads/comprehensive-code-review-mmbizked' '.claude/skills/code-review'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/comprehensive-code-review-mmbizked'

openskills read 'comprehensive-code-review-mmbizked'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/comprehensive-code-review-mmbizked/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills