code-review

Review staged changes or recent commits across five axes with file:line references.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/japurcell/skills --skill code-review-japurcell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/japurcell/skills/tree/main/skills/code-review
Command: npx skills add https://github.com/japurcell/skills --skill code-review-japurcell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates a comprehensive five-axis code review to surface correctness gaps, readability issues, architectural concerns, security risks, and performance bottlenecks in code changes.

Core Features & Use Cases

  • Five-axis evaluation across correctness, readability, architecture, security, and performance for staged changes or recent commits.
  • Actionable recommendations with precise file:line references and suggested fixes.
  • Use Case: A developer submits a PR; the skill analyzes the diff and returns a prioritized report with remediation steps.

Quick Start

Review the latest changes to the codebase and generate a structured five-axis report.

Frequently Asked Questions about code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a code review for security and architecture issues in recent commits?

Automated code review analyzes staged changes or recent commits across five axes: correctness, readability, architecture, security, and performance. It generates a structured report with file:line references, severity levels, and actionable fix recommendations to address security risks and architectural concerns.

What is five-axis code review and how does it evaluate software quality?

Five-axis code review evaluates code changes by assessing correctness, readability, architecture, security, and performance. It surfaces gaps across these dimensions, providing a prioritized report with precise file:line references and suggested fixes to improve overall software quality.

Can I get actionable fix recommendations with file and line references from a static analysis?

Static analysis provides actionable fix recommendations with precise file:line references. By evaluating staged changes or recent commits, it outputs a structured report containing clear severity levels and specific remediation steps for identified issues.

Does code review work with staged changes or do I need to commit first?

Code review works with both staged changes and recent commits across the codebase. It applies the five-axis evaluation to whichever changes are available, producing a structured report with severity levels and actionable fix recommendations.

What's the best way to find performance bottlenecks and correctness gaps in a pull request?

Finding performance bottlenecks and correctness gaps in a pull request is done by analyzing the diff across five evaluation axes. This process generates a prioritized report with file:line references and actionable remediation steps for the identified issues.

When should I not use automated code review for quality assessment?

Automated code review is not suitable when evaluating code without recent changes or staged diffs, as it requires a codebase delta to analyze. It targets specific changes to produce structured reports with file:line references and severity levels.