code-review

Analyze code submissions and PRs to provide structured feedback with severity classifications and fixes.

Updated May 29, 2023
One-click install
npx skills add https://github.com/HyperLee/Work_Memo --skill code-review-hyperlee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/HyperLee/Work_Memo/tree/main/3%E4%B9%985%E9%99%A3%E5%88%97%E5%8F%96%E7%B8%BD%E5%92%8C/.github/skills/code-review
Command: npx skills add https://github.com/HyperLee/Work_Memo --skill code-review-hyperlee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps engineers conduct thorough, senior-engineer-level code reviews with actionable feedback to improve correctness, maintainability, and security.

Core Features & Use Cases

  • Understand the context, language, and intent before commenting to produce relevant feedback.
  • Analyze code across correctness, security, performance, and maintainability, and provide concrete fixes.
  • Return feedback in a structured format using a clear output template and a risk-based depth approach for PRs, diffs, or pasted code.

Quick Start

Provide a code snippet or PR context; the reviewer follows the workflow to gather context, analyze, and produce a prioritized set of issues with actionable fixes in a senior-engineer voice.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I get actionable code review feedback for a pull request?

Code review feedback for a pull request is generated by analyzing the diff for correctness, security, and maintainability, returning prioritized issues with concrete fixes in a structured template.

What is the best way to review code for security and maintainability issues?

The best way to review code for security and maintainability is applying a senior-engineer workflow that assesses risk depth and context. It produces structured feedback classifying severity and providing concrete fixes across languages and frameworks.

Does this code review workflow work across different programming languages and frameworks?

Yes, the code review workflow works across different programming languages and frameworks by gathering context and intent before commenting, ensuring relevant feedback on correctness and performance regardless of the tech stack.

How do I analyze a code diff for correctness and performance problems?

To analyze a code diff for correctness and performance problems, submit the diff for review. The system applies a risk-based depth approach to evaluate the submission and returns structured, senior-engineer-level feedback with actionable solutions.

Can I use this to review pasted code snippets without a full pull request context?

Yes, you can use this to review pasted code snippets without a full pull request context. The reviewer follows a workflow to gather available context, analyze the code, and produce a prioritized set of issues with actionable fixes.