CO

Code Review Expert

Provides best practices and categorization for high-quality code reviews.

Install

mkdir -p .claude/skills/code-review-expert && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10757" && unzip -o skill.zip -d .claude/skills/code-review-expert && rm skill.zip

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

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.

Standards for performing high-quality, readable code reviews.
61 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Prioritize logic, security, and architecture in code reviews
  • Focus on finding bugs and design flaws
  • Group findings by severity: BLOCKER, MAJOR, NIT
  • Cross-check against P0 rules from active framework skills
  • Identify SQL Injection risks and authentication issues
  • Assess performance concerns like N+1 queries

How it works

The skill provides standards for performing high-quality code reviews, emphasizing substance over style, using a structured output format, and focusing on logic, security, and architecture.

Inputs & outputs

You give it
Code changes, pull requests
You get back
Structured code review with summary and categorized findings

When to use Code Review Expert

  • Performing code reviews
  • Analyzing PR quality
  • Security auditing

About this skill

Code Review Expert

Priority: P1 (OPERATIONAL)

Act as a Principal Engineer. Focus on logic, security, and architecture. Be constructive.

Review Principles

  • Substance > Style: Ignore formatting (leave to linters). Find bugs & design flaws.
  • Questions > Commands: "Does this handle null?" vs "Fix this."
  • Readability: Group by [BLOCKER], [MAJOR], [NIT].
  • Cross-Check: Enforce P0 rules from active framework skills (e.g. flutter/security, react/hooks).

Review Checklist (Summary)

  1. Shields Up (Security): Injection? Auth? Secrets?
  2. Performance: Big O? N+1 queries? Memory leaks?
  3. Correctness: Requirements met? Edge cases?
  4. Clean Code: DRY? SOLID? Intent-revealing names?

See references/checklist.md for full inspection list.

Output Format (Mandatory)

1. Summary: One sentence on overall quality/impact. 2. Categorized Findings:

### 🔴 [BLOCKER]

- **File**: `auth.ts`
- **Issue**: SQL Injection risk in `login`.
- **Suggestion**: Use parameterized query.
  ```typescript
  // Recommended Fix
  db.query('SELECT * FROM users WHERE id = $1', [userId]);
  ```

🟢 [NIT]

  • File: utils.ts
  • Issue: Rename d to days for clarity.

See references/output-format.md for templates.

Anti-Patterns

  • No Nitpicking: Don't flood with minor style comments.
  • No Vague Demands: "Fix this" -> Explain why and how.
  • No Ghosting: Always review tests and edge cases.

When not to use it

  • When only checking code formatting
  • When providing vague demands without explanation
  • When ignoring tests and edge cases during review

Limitations

  • Ignores formatting, leaving it to linters
  • Requires findings to be grouped by BLOCKER, MAJOR, NIT
  • Does not allow vague demands or nitpicking

How it compares

This skill enforces a structured, prioritized approach to code reviews, focusing on critical aspects like security and architecture, unlike an unstructured or style-focused review.

Compared to similar skills

Code Review Expert side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
Code Review Expert (this skill)06moNo flagsIntermediate
github-code-review132moReviewAdvanced
reviewing-code218moNo flagsIntermediate
reviewing-nextjs-16-patterns118moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry