Code Review

VerifiedSafe

Performs a comprehensive code review of changed files in git, checking for code quality, security vulnerabilities, testing coverage, and architecture adherence. Generates a structured report with blockers, suggestions, and positive notes. Use when reviewing pull requests or assessing code changes.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude CodeCursorWindsurfCopilotCodex
#code-review#git#quality#security

Recommended for

Automated summary

Performs a comprehensive code review by analyzing Git changes to assess quality, security, and maintainability.

Strengths

  • Structured analysis with categories (blockers, suggestions, etc.)
  • Security checks (injection, secrets)
  • Covers testing and architecture

Limitations

  • Relies on Git configuration for diffs
  • Not a substitute for in-depth human review
  • May miss business logic issues
When to use it

Use this skill to review code changes before merging into a main branch.

When not to use it

Do not use this for non-versioned code or when you need a global architectural review without change context.

Security analysis

Safe
Quality score90/100

The skill only uses read-only git commands and provides a review framework; no destructive, exfiltration, or obfuscated actions.

No concerns found

How this analysis is made

Examples

Review last commit
Review the code changes in the last commit. Check for quality, security, and maintainability issues.
Review pull request changes
Perform a code review on the differences between the current branch and main. Focus on security and testing.
Check for common issues
Review the recent code changes and look for any hardcoded secrets, SQL injection points, or code duplication.

name: code-review description: Perform comprehensive code review for quality, security, and maintainability. Use when reviewing code changes, PRs, or when asked to check code quality.

Code Review Skill

Instructions

  1. Identify Changed Files

    git diff --name-only HEAD~1
    # or for specific branch
    git diff --name-only main...HEAD
    
  2. Read Changed Code

    • Focus on logic changes, not just formatting
    • Understand the context and purpose
  3. Check Against Criteria

    Code Quality

    • [ ] Naming is clear and descriptive
    • [ ] Functions are focused (single responsibility)
    • [ ] No code duplication
    • [ ] Proper error handling
    • [ ] No magic numbers/strings

    Security

    • [ ] Input validation present
    • [ ] No hardcoded secrets
    • [ ] SQL injection prevention
    • [ ] XSS prevention

    Testing

    • [ ] New code has tests
    • [ ] Edge cases covered
    • [ ] Tests are meaningful

    Architecture

    • [ ] Follows project patterns
    • [ ] Dependencies flow correctly
    • [ ] No circular dependencies
  4. Generate Review Report

Output Format

## Code Review: [PR/Commit Description]

### Summary

[Brief overview of changes and overall assessment]

### Findings

#### 🔴 Blockers (Must Fix)

1. [file:line] Issue description
   - Why it's a problem
   - Suggested fix

#### 🟡 Suggestions (Should Consider)

1. [file:line] Issue description
   - Reasoning
   - Alternative approach

#### 🟢 Nitpicks (Optional)

1. [file:line] Minor suggestion

### Positive Notes

- [What was done well]

### Checklist

- [x] Code quality reviewed
- [x] Security reviewed
- [x] Tests reviewed
- [x] Architecture reviewed

Example

## Code Review: Add user authentication

### Summary

Good implementation overall. One security issue needs addressing before merge.

### Findings

#### 🔴 Blockers

1. `src/auth/login.ts:45` - Password logged in plaintext
   - Security risk: passwords visible in logs
   - Fix: Remove console.log or mask password

#### 🟡 Suggestions

1. `src/auth/login.ts:23` - Consider adding rate limiting
   - Prevents brute force attacks
   - Use existing rateLimiter middleware

#### 🟢 Nitpicks

1. `src/auth/types.ts:12` - Could use more descriptive type name
   - `LoginData` → `LoginCredentials`

### Positive Notes

- Good use of custom error types
- Comprehensive input validation
- Well-structured service layer

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-mm8o52c4/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-mm8o52c4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/code-review-mm8o52c4/download' --output '.skill-downloads/code-review-mm8o52c4/SKILL.md.part' && mv '.skill-downloads/code-review-mm8o52c4/SKILL.md.part' '.skill-downloads/code-review-mm8o52c4/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-mm8o52c4/SKILL.md' && test -s '.skill-downloads/code-review-mm8o52c4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/code-review' && cp -R '.skill-downloads/code-review-mm8o52c4' '.claude/skills/code-review'

Cursor
test -f '.skill-downloads/code-review-mm8o52c4/SKILL.md' && test -s '.skill-downloads/code-review-mm8o52c4/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/code-review' && cp -R '.skill-downloads/code-review-mm8o52c4' '.cursor/skills/code-review'

Codex
test -f '.skill-downloads/code-review-mm8o52c4/SKILL.md' && test -s '.skill-downloads/code-review-mm8o52c4/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/code-review' && cp -R '.skill-downloads/code-review-mm8o52c4' '.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-mm8o52c4'

openskills read 'code-review-mm8o52c4'

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-mm8o52c4/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