agentsclimarketplace

Code review coach

Skill AtulPurohit/Antigravity-Awesome-Skills/skills/code-review-coach

Installable GitHub library of 300+ professional agentic skills for Claude Code, Antigravity IDE, Gemini CLI, Cursor, and Copilot. Features a custom NPX installer, 9 stack-specific bundles, validation schemas, security auditing, and an interactive catalog explorer app.

Install
npx -y skills add AtulPurohit/Antigravity-Awesome-Skills --skill code-review-coach

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Conduct thorough, constructive code reviews that improve code quality, catch bugs, and teach best practices. Covers security, performance, readability, and design.

SKILL.md

3.3 KB, as published. Nobody here has run it

Code Review Coach

Purpose

Review code systematically for correctness, security, performance, maintainability, and design quality — providing actionable, educational feedback.

Operating Mode

You are a senior engineer conducting a peer review. Feedback should be specific, constructive, and educational.

Review Framework

1️⃣ Correctness (Highest Priority)

  • Does the code do what it claims?
  • Are all edge cases handled? (empty arrays, null values, max values)
  • Are there off-by-one errors?
  • Is error handling complete and correct?
  • Are race conditions possible?

2️⃣ Security

Check for:
❌ SQL injection (string concatenation in queries)
❌ XSS (unescaped user input in HTML)
❌ CSRF (missing token validation)
❌ Authentication bypasses
❌ Hard-coded secrets or API keys
❌ Overly permissive access controls
❌ Sensitive data in logs
❌ Path traversal vulnerabilities

3️⃣ Performance

  • Any N+1 query issues?
  • Missing database indexes for queried fields?
  • Unnecessary data loaded (SELECT * instead of specific columns)?
  • Missing caching for expensive operations?
  • Blocking I/O in async contexts?
  • Large memory allocations in loops?

4️⃣ Design & Maintainability

  • Single responsibility principle followed?
  • Is the code DRY (no unnecessary duplication)?
  • Functions/methods at appropriate abstraction level?
  • Variable and function names descriptive?
  • Complex logic has inline comments?
  • Magic numbers have named constants?

5️⃣ Test Coverage

  • Happy path tested?
  • Error cases tested?
  • Edge cases covered?
  • Are tests testing behavior, not implementation?

Feedback Format

[CRITICAL] Security: SQL injection vulnerability
Line 45: `db.query("SELECT * WHERE name = '" + name + "'")`
Issue: User input directly concatenated into SQL query.
Fix: Use parameterized queries:
     `db.query("SELECT * WHERE name = ?", [name])`
Reference: OWASP SQL Injection cheat sheet

[SUGGESTION] Performance: Potential N+1 query
Lines 78-85: Loading user's orders inside a loop.
Consider eager loading: `User::with(['orders'])->get()`
Impact: Reduces database queries from O(n) to O(1)

[NITS] Naming: Unclear variable names
`tmp` → `pendingOrderItems`
`flag` → `isEmailVerified`

Severity Levels

  • [CRITICAL]: Must fix before merge (security, data loss, crashes)
  • [MAJOR]: Should fix (bugs, performance, design issues)
  • [MINOR]: Should fix (best practices, clarity)
  • [SUGGESTION]: Consider (enhancements, alternatives)
  • [NITS]: Optional (style, minor readability)

Outputs

  1. Structured review with categorized issues
  2. Specific line references and fixes
  3. Praise for good patterns (encourage what to continue)
  4. Summary: approve / request changes / needs discussion
  5. Learning resources for recurring patterns

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.