Skip to main content
skill CX Codex

reviewing-code — Claude Code skill: step-by-step code review

A skill that walks your code through a checklist: correctness, maintainability, performance, types and tests. Useful when a change needs review before merge.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add spencerpauly/awesome-cursor-skills --skill reviewing-code -a claude-code
Open on GitHub

What reviewing-code does

The skill kicks in when you ask for a code review or feedback on your code. It reads the files or the diff first and works out the scope: new feature, bug fix or refactor. Then it goes down the list.

Correctness covers empty input, null, zero and negative numbers, error states via try/catch and fallback UI, race conditions and timeouts in async code, off-by-one errors in loops. Maintainability looks at single-responsibility functions, descriptive names, duplication worth extracting, magic numbers, deep nesting. Performance checks for N+1 query patterns, expensive work inside render loops, large lists without virtualization or pagination, missing indexes for common queries. On TypeScript projects it also flags any types, missing return types on public APIs and non-exhaustive union handling.

Findings come sorted into three buckets: must fix (bugs, security, data loss), should fix (performance, maintainability) and nit (style). Each one lists the file, the line, the issue and a suggested fix. The skill asks the agent to explain why something is a problem and to call out what was done well. Style points a linter or formatter already handles are left alone.

What it helps with

  • review a diff before merge and catch bugs
  • check how empty input and null are handled
  • spot N+1 query patterns in database access
  • narrow any types in a TypeScript codebase
  • see whether tests cover error cases, not just the happy path

Example prompts for the agent

  • review this diff
  • check src/api/orders.ts for correctness and performance
  • look at the branch changes and sort findings by severity

How to install reviewing-code

1Skills CLI (Vercel)

npx skills add spencerpauly/awesome-cursor-skills --skill reviewing-code -a claude-code

2Manually: put the files in place

~/.claude/skills/reviewing-code/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/reviewing-code/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about reviewing-code

How do I install reviewing-code in Claude?

Run npx skills add spencerpauly/awesome-cursor-skills --skill reviewing-code -a claude-code. The skill lands in ~/.claude/skills/reviewing-code/SKILL.md.

What does reviewing-code do?

It runs code through a checklist: correctness, maintainability, performance, types and tests. You get findings with the file, line and a suggested fix.

Which platforms support the skill?

Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. Each platform has its own install command.

Source text

SKILL.md · CC0-1.0
---
name: reviewing-code
description: Perform a thorough code review focused on correctness, maintainability, performance, and best practices.
---

# Code Review

Use this skill when the user asks for a code review, feedback on their code, or to check code quality.

## Steps

1. **Understand the change** — read the files or diff to understand what the code is supposed to do. Identify the scope (new feature, bug fix, refactor).

2. **Check correctness**
   - Does the code handle edge cases (empty input, null, zero, negative numbers)?
   - Are error states handled (try/catch, error boundaries, fallback UI)?
   - Does async code handle race conditions, cancellation, and timeouts?
   - Are there off-by-one errors in loops or array access?

3. **Check maintainability**
   - Are functions focused on a single responsibility?
   - Are variable and function names descriptive?
   - Is there unnecessary duplication that should be extracted?
   - Are magic numbers replaced with named constants?
   - Is the code complexity reasonable (deeply nested conditionals, long functions)?

4. **Check performance**
   - Are there N+1 query patterns in database access?
   - Are expensive computations or API calls happening in render loops?
   - Are large lists missing virtualization or pagination?
   - Are there missing indexes for common database queries?
   - Is memoization used appropriately (not over-applied)?

5. **Check type safety** (TypeScript projects)
   - Are there `any` types that should be narrowed?
   - Are function return types explicit for public APIs?
   - Are union types handled exhaustively?

6. **Check testing**
   - Are there tests for the new/changed code?
   - Do tests cover the happy path AND error cases?
   - Are tests isolated (no shared mutable state)?

7. **Provide feedback** — organize findings by severity:
   - **Must fix**: bugs, security issues, data loss risks
   - **Should fix**: performance issues, maintainability concerns
   - **Nit**: style preferences, minor suggestions

   For each finding, include the file, line, the issue, and a suggested fix.

## Notes

- Be constructive — explain *why* something is a problem, not just that it is.
- Acknowledge what's done well, not just what needs fixing.
- Don't bikeshed on style issues that a linter/formatter should handle.

© spencerpauly · CC0-1.0 · spencerpauly/awesome-cursor-skills

Similar skills

All skills for Code review and refactoring →

From the same set60

systematic-debugging Enforces a structured debugging workflow on your AI assistant instead of random edits. It helps isolate elusive bugs and verify root causes with evidence. CX Codex +1 545installs verifying-in-browser Starts the dev server after code changes, opens the app in a browser and checks rendering, console errors and network health. CX Codex +1 540installs using-ui-stack Makes the agent build interfaces from fixed rules: an 8px grid, 60-30-10 colors, type scale, dark mode and interaction states. CX Codex +1 539installs parallel-code-review Runs four parallel read-only subagents to inspect a diff across security, speed, correctness, and readability. Built for vetting large or risky pull requests. CX Codex +1 530installs writing-tests Inspects existing code, detects your test runner, and drafts unit and integration tests with mocks and edge cases. CX Codex +1 499installs api-smoke-testing Finds API endpoints across your codebase, spins up the local dev server, and tests every route with curl. Spots unmounted 404 routes and 500 server crashes before release. CX Codex +1 495installs saving-workspace-context The skill writes research, decisions and templates into your workspace files, so the next session starts with context instead of a blank slate. CX Codex +1 495installs codebase-onboarding Fires five explore subagents in parallel to cover architecture, data models, APIs, auth and deployment, then merges their findings into one onboarding doc. CX Codex +1 476installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor