A systematic guide for reviewing pull requests, focusing on critical issues over trivial nits.

Install

mkdir -p .claude/skills/code-review-letsgettoworkbro && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14441" && unzip -o skill.zip -d .claude/skills/code-review-letsgettoworkbro && rm skill.zip

Installs to .claude/skills/code-review-letsgettoworkbro

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.

Use this skill for code review and PR review tasks. Covers review methodology, what to flag, what to skip, and output structure.
128 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Understand PR purpose and scope using `gh pr view`
  • Read the full diff using `gh pr diff`
  • Focus on correctness, security, reliability, and performance issues
  • Identify breaking changes and assess test coverage
  • Output findings with severity, location, description, and suggested fix

How it works

This skill uses `gh pr view` and `gh pr diff` to understand a pull request. It then focuses on substantive issues like correctness and security, prioritizing them over style, and outputs structured findings.

Inputs & outputs

You give it
A GitHub pull request number
You get back
A structured code review report with findings, severity levels, and an overall summary

When to use code-review

  • Conducting a comprehensive PR review
  • Identifying security risks in new code
  • Checking for breaking API changes

About this skill

Code Review

Review a GitHub pull request for substantive issues. Focus on what matters, skip what doesn't.

Steps

  1. Run gh pr view {pr_number} --json title,body,files to understand the PR's purpose and scope.
  2. Run gh pr diff {pr_number} to read the full diff.
  3. Before commenting, read surrounding code to understand full context — a pattern that looks wrong in isolation may be an established convention.

Focus Areas (priority order)

  1. Correctness — Logic bugs, edge cases, error handling
  2. Security — Input validation, injection risks, secrets exposure
  3. Reliability — Race conditions, failure modes, resource leaks
  4. Performance — Inefficient algorithms, N+1 queries, unnecessary work
  5. Breaking changes — API/behavior changes affecting callers
  6. Test coverage — Are new code paths tested?

Skip style/formatting unless it materially impacts readability. Do not nitpick naming, style preferences, or issues linters catch.

Severity Levels

  • Blocking: Must fix before merge (bugs, security, significant reliability/performance issues, breaking changes)
  • Non-blocking: Suggestions for improvement (optional)

Output Format

Findings

For each issue found:

[Issue Title]

  • Severity: blocking | non-blocking
  • Location: file_path:line_number
  • Description: What the issue is and why it matters
  • Suggested Fix: Concrete code change or approach

If no issues found, state that the changes look correct and explain why.

Summary

Overall assessment: is the PR ready to merge, or does it need changes? List the most important issues if any.

When not to use it

  • When the primary concern is style or formatting issues that linters catch
  • When nitpicking naming or style preferences is the goal
  • When a shallow review is sufficient without understanding full context

Limitations

  • It skips style/formatting unless it materially impacts readability
  • It does not nitpick naming, style preferences, or issues linters catch
  • The review is focused on substantive issues, not complete code quality

How it compares

This skill provides a prioritized and structured methodology for code review, focusing on substantive issues and skipping style nitpicks, which is more efficient than an unstructured manual review.

Compared to similar skills

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

SkillInstallsUpdatedSafetyDifficulty
code-review (this skill)03moNo flagsIntermediate
effective-go3239moNo flagsBeginner
architect-review1094moNo flagsAdvanced
resolve-conflicts818moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

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

Search skills

Search the agent skills registry