Tags

Best Code Review Skills for AI Agents

1326 Code Review skills for AI coding assistants — ranked by popularity.

This collection provides targeted skill definitions for AI agents designed to improve your code review workflow. These files are built for developers using Claude Code, Codex, or Cursor who need specialized guidance during pull request reviews or architectural audits. By importing these skills, your agent gains the ability to apply specific standards like SOLID principles for object-oriented design or the idiomatic conventions found in Effective Go. Beyond style, you can deploy agents to handle complex maintenance tasks such as dependency upgrades, systematic testing patterns in Python, or searching external repository context via GitHub issues. Whether you are performing a deep-dive architect review, resolving merge conflicts, or refactoring for better abstractions, these modular skills allow you to automate the repetitive aspects of human-led code reviews. They transform your editor into a consistent partner that enforces your project's technical standards without manual intervention.

Top Code Review skills

effective-go

openshift

Apply Go best practices, idioms, and conventions from golang.org/doc/effective_go. Use when writing, reviewing, or refactoring Go code to ensure idiomatic, clean, and efficient implementations.

323536

architect-review

sickn33

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

109320

resolve-conflicts

antinomyhq

Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.

81334

solid-principles

SmidigStorm

Enforce SOLID principles (Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion) in object-oriented design. Use when writing or reviewing classes and modules.

57236

python-testing-patterns

wshobson

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

77204

codex

Lucklyric

Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.

32238

dependency-upgrade

wshobson

Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.

26240

typescript-review

metabase

Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing TypeScript/JavaScript code.

39178

error-handling-patterns

wshobson

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

35170

deepwiki-rs

sopaco

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.

25170

claude-automation-recommender

anthropics

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

47140

accessibility-compliance

wshobson

Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.

45132

test-cases

cexll

This skill should be used when generating comprehensive test cases from PRD documents or user requirements. Triggers when users request test case generation, QA planning, test scenario creation, or need structured test documentation. Produces detailed test cases covering functional, edge case, error handling, and state transition scenarios.

57115

ast-grep

ast-grep

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.

17135

github-code-review

ruvnet

Comprehensive GitHub code review with AI-powered swarm coordination

13135

codex-claude-loop

bear2u

Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality

13132

senior-fullstack

davila7

Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.

35110

typescript-write

metabase

Write TypeScript and JavaScript code following Metabase coding standards and best practices. Use when developing or refactoring TypeScript/JavaScript code.

30114

using-serena-for-exploration

seanGSISG

Use when exploring codebases with Serena MCP tools for architectural understanding and pattern discovery - guides efficient symbolic exploration workflow minimizing token usage through targeted symbol reads, overview tools, and progressive narrowing

9127

shellcheck-configuration

wshobson

Master ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure, fixing code issues, or ensuring script portability.

9126

v3-ddd-architecture

ruvnet

Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

12121

git-commits

bonny

Create well-structured git commits in logical chunks following best practices

21109

confidence-check

SuperClaude-Org

Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.

13114

reviewing-code

CaptainCrouton89

Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.

21105

How to choose a Code Review skill

Select skills based on the technical stack and specific challenges of your current codebase. Review the description for each file to ensure its domain—such as architectural patterns, test automation, or dependency management—matches your immediate needs. Look for high-maintenance skills that integrate directly with your language-specific tools like pytest or go-fmt. Prioritize skills that provide clear, actionable instructions rather than general advice. If your review process involves frequent cross-repository research, choose skills like context7 to gain deeper insight into your external dependencies.

More Code Review skills

codex-skill
feiskyer · 12 installs
wcag-audit-patterns
wshobson · 20 installs
reviewing-nextjs-16-patterns
djankies · 11 installs
code-coverage-with-gcov
gadievron · 15 installs
angular-best-practices
sickn33 · 21 installs
serena
massgen · 15 installs
clojure-review
metabase · 14 installs
go-dev-guidelines
jumppad-labs · 14 installs
git-advanced-workflows
wshobson · 11 installs
conversation-analyzer
mhattingpete · 8 installs
software-security
project-codeguard · 21 installs
subagent-driven-development
davila7 · 14 installs
cursor-explorer-mcp
sepiabrown · 6 installs
documentation-review
stacklok · 11 installs
typescript
lobehub · 28 installs
github-multi-repo
ruvnet · 6 installs
specification-architect
adrianpuiu · 13 installs
validate-openapi-specs
epieczko · 5 installs
code-refactoring-refactor-clean
sickn33 · 24 installs
seo-audit
davila7 · 29 installs
at-dispatch-v2
pytorch · 5 installs
dbt-transformation-patterns
wshobson · 6 installs
docs-review
metabase · 10 installs
workthrough
bear2u · 10 installs
git-workflow-enforcer
CrazyDubya · 8 installs
validate-typescript
BerryKuipers · 5 installs
ai-assisted-development
baz-scm · 5 installs
fix-dependabot-alerts
microsoft · 18 installs
wolf-scripts-core
Nice-Wolf-Studio · 5 installs
claude-md-improver
anthropics · 21 installs
python-design-patterns
wshobson · 19 installs
coding-agent
openclaw · 16 installs
ts-testing
johnlindquist · 6 installs
code-reviewer
google-gemini · 24 installs
frontend-code-review
langgenius · 11 installs
codebase-cleanup-refactor-clean
sickn33 · 16 installs
python-code-style
wshobson · 9 installs
env-manager
CuriousLearner · 5 installs
code-review-excellence
wshobson · 19 installs
code-walk-thru
pchalasani · 6 installs
cookbook-audit
anthropics · 5 installs
code-review
agno-agi · 26 installs
backend-security-coder
sickn33 · 24 installs
ruby-coder
majesticlabs-dev · 5 installs
equilateral-agents
Equilateral-AI · 5 installs
gh-address-comments
openai · 10 installs
verification-before-completion
obra · 9 installs
react-best-practices
redpanda-data · 22 installs
clean-code
davila7 · 12 installs
golang-patterns
affaan-m · 9 installs
pair-programming
ruvnet · 6 installs
salesforce-development
davila7 · 14 installs
php-best-practices
HoangNguyen0403 · 15 installs
test-driven-development
obra · 12 installs
react-patterns
davila7 · 9 installs
anti-slop
rand · 12 installs
agent-md-refactor
davila7 · 7 installs
fact-check
leonardomso · 7 installs
woocommerce-code-review
woocommerce · 6 installs
schema-markup
davila7 · 10 installs
top-100-web-vulnerabilities-reference
davila7 · 5 installs
coding-standards
affaan-m · 7 installs
final-release-review
openai · 5 installs
github-search
parcadei · 6 installs
agent-researcher
ruvnet · 4 installs
review
parcadei · 7 installs
agentic-eval
github · 6 installs
feature-flags
facebook · 6 installs
php-pro
sickn33 · 13 installs
receiving-code-review
obra · 3 installs
codemap
JordanCoin · 8 installs
differential-review
trailofbits · 31 installs
mutation-testing
metabase · 5 installs
refactor
github · 8 installs
backend-to-frontend-handoff-docs
davila7 · 3 installs
premortem
parcadei · 9 installs
fix
facebook · 5 installs
pr-review
pytorch · 6 installs
typescript-code-review
anyproto · 13 installs
verify
facebook · 6 installs
flow
facebook · 7 installs
requesting-code-review
obra · 5 installs
omo
cexll · 1 installs
parallel-agents
davila7 · 6 installs
pytest
prowler-cloud · 8 installs
security-audit
ruvnet · 3 installs
antfu
antfu · 6 installs
finishing-a-development-branch
obra · 4 installs
python-patterns
affaan-m · 6 installs
behavioral-modes
davila7 · 3 installs
javascript-mastery
davila7 · 7 installs
playwright-validation
open-metadata · 3 installs
security
parcadei · 5 installs
address-github-comments
davila7 · 3 installs
angular-migration
sickn33 · 10 installs
git
EpicenterHQ · 8 installs

+1,206 more — browse all skills.

Frequently asked

Can I combine multiple skills for a single code review?
Yes. You can stack these skills to create a multi-faceted review process. For example, you might combine the architect-review skill with solid-principles to ensure that your code follows both high-level design patterns and low-level clean code practices. Each skill acts as a focused module, allowing your agent to handle distinct layers of a code review simultaneously.
How do these skills handle merge conflicts during a review?
The resolve-conflicts skill is designed to manage the process of fixing merge conflicts. It focuses on identifying and structuring the resolution steps rather than attempting to guess the merge result itself. It acts as a safety layer, ensuring your agent follows a specific protocol when it detects conflicting code blocks during your review workflow.

Browse other tags

Search skills

Search the agent skills registry