Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
aj-geddes avatar

Code Review Analysis

  • 2.3k installs
  • 305 repo stars
  • Updated March 4, 2026
  • aj-geddes/useful-ai-prompts

code-review-analysis is a prompt skill for systematic PR reviews across quality, security, performance, and testing.

About

The code-review-analysis skill structures comprehensive reviews across code quality, security, performance, maintainability, and standards compliance. It targets pull request and merge request review, pre-merge quality checks, vulnerability identification, and mentoring through constructive feedback. Quick start uses git diff main...feature-branch, git diff --stat for scope, and git log --oneline for commit history context. Reference guides split work into initial assessment, code quality analysis, security review, performance review, testing review, and best practices files under references/. DO guidance emphasizes respectful tone, explaining why behind suggestions, code examples, clarifying questions, acknowledging good patterns, focusing on important issues, and offering pairing on complex fixes. DON'T guidance warns against personal criticism, style nitpicks better handled by automation, blocking on subjective taste, reviewing more than about four hundred lines at once, skipping tests, ignoring security, or rushing. The overview positions the process as systematic industry-standard review rather than ad hoc commentary.

  • Covers quality, security, performance, maintainability, and standards.
  • Quick start uses git diff and log against the base branch.
  • Reference guides split assessment, security, performance, and testing.
  • Encourages constructive feedback with examples and context awareness.
  • Avoid reviewing more than about 400 lines or skipping test coverage.

Code Review Analysis by the numbers

  • 2,336 all-time installs (skills.sh)
  • +20 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #69 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

code-review-analysis capabilities & compatibility

Capabilities
git diff and commit history based review start · modular reference guides per review dimension · constructive feedback and mentoring practices · security and performance emphasis in review scop · anti patterns for nitpicks and oversized reviews
Use cases
code review · security audit · testing
From the docs

What code-review-analysis says it does

Systematic code review process covering code quality, security, performance, maintainability, and best practices
SKILL.md
Review too many changes at once (>400 lines)
SKILL.md
npx skills add https://github.com/aj-geddes/useful-ai-prompts --skill code-review-analysis

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2.3k
repo stars305
Security audit3 / 3 scanners passed
Last updatedMarch 4, 2026
Repositoryaj-geddes/useful-ai-prompts

How should I review this pull request thoroughly and constructively before merging?

Run systematic pull request reviews covering quality, security, performance, testing, and constructive feedback using reference guides.

Who is it for?

Reviewing pull requests, merge requests, or pre-merge quality and security checks.

Skip if: Skip for automated lint-only fixes or writing new features without a review request.

When should I use this skill?

User asks for code review, PR analysis, security check on changes, or merge feedback.

What you get

A structured review covering diffs, risks, tests, and actionable suggestions with respectful tone.

  • Structured review comments
  • Security and quality findings

Files

SKILL.mdMarkdownGitHub ↗

Code Review Analysis

Table of Contents

Overview

Systematic code review process covering code quality, security, performance, maintainability, and best practices following industry standards.

When to Use

  • Reviewing pull requests and merge requests
  • Analyzing code quality before merging
  • Identifying security vulnerabilities
  • Providing constructive feedback to developers
  • Ensuring coding standards compliance
  • Mentoring through code review

Quick Start

Minimal working example:

# Check the changes
git diff main...feature-branch

# Review file changes
git diff --stat main...feature-branch

# Check commit history
git log main...feature-branch --oneline

Reference Guides

Detailed implementations in the references/ directory:

GuideContents
Initial AssessmentInitial Assessment
Code Quality AnalysisCode Quality Analysis
Security ReviewSecurity Review
Performance ReviewPerformance Review
Testing ReviewTesting Review
Best PracticesBest Practices

Best Practices

✅ DO

  • Be constructive and respectful
  • Explain the "why" behind suggestions
  • Provide code examples
  • Ask questions if unclear
  • Acknowledge good practices
  • Focus on important issues
  • Consider the context
  • Offer to pair program on complex issues

❌ DON'T

  • Be overly critical or personal
  • Nitpick minor style issues (use automated tools)
  • Block on subjective preferences
  • Review too many changes at once (>400 lines)
  • Forget to check tests
  • Ignore security implications
  • Rush the review

Related skills

How it compares

Pick code-review-analysis for narrative PR feedback across quality dimensions; use a linter skill for rule-by-rule static analysis only.

FAQ

What git commands start the review?

Use git diff main...feature-branch, git diff --stat, and git log main...feature-branch --oneline.

How large should a single review be?

Avoid reviewing more than about 400 changed lines at once; split large diffs.

Where are detailed checklists?

Load references for initial assessment, security, performance, testing, and best practices.

Is Code Review Analysis safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.