agentleFS
Sign inStart free
peopleforresterpeopleforrester/claude-dotfiles/skills/development/code-reviewer/SKILL.md

code-reviewer

Skill3 starsChanged 7 months agoMITView on GitHub

Systematic code review for pull requests and code changes. Use when the user asks for a code review, PR review, or wants feedback on code quality. Provides structured feedback on correctness, security, performance, and maintainability.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 146 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before deploying to production

    line 27
  2. Distinctive:

    Use "we" and "let's" not "you should"

    line 177
  3. Distinctive:

    Ask questions when intent is unclear

    line 178
  4. Distinctive:

    If something is unclear:

    line 183

“Common” is measured: kept by at least 6 in 10 of the 146 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Review Assistant

Systematic approach to reviewing code changes for quality and correctness.

When to Use

  • User asks for a code review or PR review
  • Reviewing changes before merging
  • User asks "is this code okay?" or "any issues with this?"
  • Before deploying to production

Review Process

1. Understand Context

Before reviewing code:

  • What is the purpose of this change?
  • What problem does it solve?
  • Are there related issues or documentation?

2. Review in Layers

Review code systematically in this order:

Layer 1: Correctness     - Does it work as intended?
Layer 2: Security        - Are there vulnerabilities?
Layer 3: Performance     - Are there bottlenecks?
Layer 4: Maintainability - Is it readable and extensible?
Layer 5: Style           - Does it follow conventions?

Review Checklist

Correctness

  • Logic handles all expected cases
  • Edge cases considered (empty, null, boundaries)
  • Error handling is appropriate
  • No obvious bugs or typos
  • Tests cover the changes

Security

  • No hardcoded secrets or credentials
  • User input is validated and sanitized
  • SQL queries use parameterized statements
  • No XSS vulnerabilities (user data escaped)
  • Authentication/authorization checked
  • Sensitive data not logged

Performance

  • No N+1 query problems
  • Large datasets paginated
  • Expensive operations cached if appropriate
  • No unnecessary re-renders (React)
  • Async operations where beneficial

Maintainability

  • Code is readable without extensive comments
  • Functions are focused and reasonably sized
  • No code duplication (DRY)
  • Clear naming for variables and functions
  • Appropriate abstraction level

Style

  • Follows project conventions
  • Consistent formatting
  • No commented-out code
  • Imports organized

Feedback Format

Structure feedback as:

## Summary

Brief overview of the change and overall assessment.

## Must Fix (Blocking)

Issues that must be addressed before merge.

### Issue 1: [Title]
**Location**: `file.ts:42`
**Problem**: Description of the issue
**Suggestion**: How to fix it

## Should Fix (Non-blocking)

Improvements that should be made but don't block merge.

## Consider (Optional)

Suggestions for future improvement.

## Positive Feedback

What was done well.

Examples

Security Issue

### Issue: SQL Injection Vulnerability
**Location**: `users.ts:28`
**Problem**: User input directly concatenated into SQL query
**Suggestion**: Use parameterized query:
\`\`\`typescript
// Before
const query = `SELECT * FROM users WHERE id = ${userId}`;

// After
const query = 'SELECT * FROM users WHERE id = $1';
const result = await db.query(query, [userId]);
\`\`\`

Performance Issue

### Issue: N+1 Query in Loop
**Location**: `orders.ts:15-20`
**Problem**: Database query inside loop causes N+1 queries
**Suggestion**: Fetch all related data in single query:
\`\`\`typescript
// Before: N+1 queries
for (const order of orders) {
  order.items = await db.getItems(order.id);
}

// After: 2 queries
const orderIds = orders.map(o => o.id);
const allItems = await db.getItemsByOrderIds(orderIds);
\`\`\`

Positive Feedback

## Positive Feedback

- Good separation of concerns between service and repository layers
- Comprehensive error handling with specific error types
- Well-structured tests covering edge cases

Review Tone

  • Be constructive, not critical
  • Explain the "why" behind suggestions
  • Acknowledge good work
  • Use "we" and "let's" not "you should"
  • Ask questions when intent is unclear
  • Distinguish between must-fix and nice-to-have

Questions to Ask

If something is unclear:

  • "What's the expected behavior when X happens?"
  • "Is there a reason this approach was chosen over Y?"
  • "Could you help me understand this section?"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free