code-review
A systematic 3-pass review process for code quality, focusing on logic, security, and professional growth.
Install
mkdir -p .claude/skills/code-review-fabioc-aloha && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15083" && unzip -o skill.zip -d .claude/skills/code-review-fabioc-aloha && rm skill.zipInstalls to .claude/skills/code-review-fabioc-aloha
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.
Systematic code review for correctness, security, and growth — not just style enforcementKey capabilities
- →Prioritize correctness, security, and maintainability in reviews
- →Conduct a 3-pass review focusing on orientation, logic, and polish
- →Use comment prefixes to categorize feedback for authors
- →Check for security vulnerabilities like injection and secrets in code
- →Verify logic for edge cases, error paths, and async operations
- →Assess architectural adherence and new dependency justification
How it works
The skill systematically reviews code by prioritizing correctness, security, and maintainability through a 3-pass process. It uses comment prefixes to organize feedback and includes checklists for security, logic, quality, and architecture.
Inputs & outputs
When to use code-review
- →Conducting a comprehensive PR review
- →Checking for security vulnerabilities
- →Assessing code maintainability
About code-review
Prioritizes logic deep-dives, security checks, and maintainability. Uses comment prefixes to organize feedback for authors.
Systematic code review for correctness, security, and growth — not just style enforcement
When not to use it
- →When the review is solely for style enforcement
- →When the PR size is 1000+ lines, requiring a breakdown
- →When reviews repeatedly miss security or correctness defects that adversarial review catches
Limitations
- →The skill focuses on correctness, security, and maintainability, not just style.
- →PRs of 1000+ lines should be refused and broken down.
- →NASA standards are triggered only for mission-critical projects.
How it compares
This skill provides a structured, prioritized, and educational approach to code review with specific comment prefixes and a 3-pass system, aiming to teach authors and catch critical issues beyond just style.
Compared to similar skills
code-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-review (this skill) | 0 | 5mo | No flags | Advanced |
| github-code-review | 13 | 6mo | Review | Advanced |
| reviewing-code | 21 | 12mo | No flags | Intermediate |
| reviewing-nextjs-16-patterns | 11 | 12mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by fabioc-aloha
View all by fabioc-aloha →You might also like
github-code-review
ruvnet
Comprehensive GitHub code review with AI-powered swarm coordination
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.
reviewing-nextjs-16-patterns
djankies
Review code for Next.js 16 compliance - security patterns, caching, breaking changes. Use when reviewing Next.js code, preparing for migration, or auditing for violations.
cookbook-audit
anthropics
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
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.