Code Review

VerifiedSafe

Performs structured code reviews by analyzing correctness, security, maintainability, and performance. Provides actionable feedback with severity levels and a summary. Ideal when reviewing pull requests or code changes for quality assurance.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude CodeCursorWindsurfCopilotCodex
#code-review#pull-requests#code-quality#best-practices#security

Recommended for

Automated summary

Performs structured code reviews in multiple passes (correctness, security, maintainability, performance) and provides organized feedback with severity levels.

Strengths

  • Systematic multi-pass process covering critical aspects
  • Clear feedback format with categories (summary, positives, suggestions, questions)
  • Issue prioritization by severity (blocker, should fix, nitpick)

Limitations

  • May miss context-specific vulnerabilities (e.g., complex business logic)
  • Requires a good PR description to understand context
  • Performance suggestions are generic and may not suit all environments
When to use it

Ideal for getting a fast, structured review of a pull request or diff, especially for spotting security or maintainability issues.

When not to use it

Avoid for code that is still exploratory or not finalized, as the level of detail may slow down rapid iteration.

Security analysis

Safe
Quality score90/100

The skill provides only instructional guidance for code review, with no execution of commands, tools, or risk of destructive actions. It does not instruct the AI to exfiltrate data, disable safety, or run arbitrary code.

No concerns found

How this analysis is made

Examples

Review a PR with security focus
Review this pull request for security issues. Look for input validation, hardcoded secrets, and OWASP top 10 risks.
Quick code review for correctness
Review this code diff for logic errors and edge cases. Summarize with severity levels.

name: code-review description: Perform thorough code reviews on pull requests, diffs, or code changes. Use when asked to review code, check a PR, or provide feedback on changes.

Code Review

A structured approach to reviewing code changes.

Instructions

When reviewing code, follow this process:

1. Understand the Context

Before diving into the code:

  • Read the PR description or commit message
  • Understand what problem is being solved
  • Note any linked issues or requirements

2. Review in Passes

Make multiple passes through the code:

First pass — Correctness

  • Does the code do what it claims to do?
  • Are there logic errors or edge cases missed?
  • Could this break existing functionality?

Second pass — Security

  • Input validation present where needed?
  • No hardcoded secrets or credentials?
  • SQL injection, XSS, or other OWASP top 10 risks?

Third pass — Maintainability

  • Is the code readable and well-organized?
  • Are names clear and consistent?
  • Is complexity justified?

Fourth pass — Performance

  • Any obvious inefficiencies (N+1 queries, unnecessary loops)?
  • Appropriate data structures used?
  • Resource cleanup handled?

3. Provide Feedback

Structure your review:

## Summary
[One sentence overall assessment]

## What's Good
- [Positive observations]

## Suggestions
- [Actionable improvements, ordered by importance]

## Questions
- [Clarifying questions if any]

4. Severity Levels

Categorize issues:

  • Blocker — Must fix before merge (bugs, security issues)
  • Should fix — Important but not blocking
  • Nitpick — Style preferences, minor suggestions

Examples

Example Review Output

## Summary
Solid implementation of user authentication. One security issue needs addressing before merge.

## What's Good
- Clean separation of auth logic from route handlers
- Good use of bcrypt for password hashing
- Comprehensive error handling

## Suggestions
1. **[Blocker]** Line 45: Password reset token should use `crypto.randomBytes(32)` instead of `Math.random()` — predictable tokens are a security risk
2. **[Should fix]** Line 78: Consider adding rate limiting to prevent brute force attempts
3. **[Nitpick]** Line 12: Typo in variable name `authetication` → `authentication`

## Questions
- Is there a reason we're storing sessions in memory rather than Redis? This won't scale across multiple instances.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/code-review-mma3js3l/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/code-review-mma3js3l' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/code-review-mma3js3l/download' --output '.skill-downloads/code-review-mma3js3l/SKILL.md.part' && mv '.skill-downloads/code-review-mma3js3l/SKILL.md.part' '.skill-downloads/code-review-mma3js3l/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/code-review-mma3js3l/SKILL.md' && test -s '.skill-downloads/code-review-mma3js3l/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/code-review' && cp -R '.skill-downloads/code-review-mma3js3l' '.claude/skills/code-review'

Cursor
test -f '.skill-downloads/code-review-mma3js3l/SKILL.md' && test -s '.skill-downloads/code-review-mma3js3l/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/code-review' && cp -R '.skill-downloads/code-review-mma3js3l' '.cursor/skills/code-review'

Codex
test -f '.skill-downloads/code-review-mma3js3l/SKILL.md' && test -s '.skill-downloads/code-review-mma3js3l/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/code-review' && cp -R '.skill-downloads/code-review-mma3js3l' '.agents/skills/code-review'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/code-review-mma3js3l'

openskills read 'code-review-mma3js3l'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/code-review-mma3js3l/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills