review-code

Review code, specs, and proposals with structured BLOCKER/IMPROVEMENT/PRAISE classifications.

4|1|Updated Dec 30, 2025
One-click install
npx skills add https://github.com/lushly-dev/afd --skill review-code-lushly-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-code
Source: https://github.com/lushly-dev/afd/tree/main/.claude/skills/review-code
Command: npx skills add https://github.com/lushly-dev/afd --skill review-code-lushly-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of reviewing code, specifications, and proposals, ensuring quality, security, and adherence to best practices by leveraging AI and structured checklists.

Core Features & Use Cases

  • Research-Grounded Reviews: Opinions are backed by codebase searches and web research, not just AI knowledge.
  • Multi-Dimensional Checklists: Covers code quality, security, testing, performance, and documentation.
  • Structured Feedback: Findings are classified as BLOCKER, IMPROVEMENT, or PRAISE with clear evidence and suggestions.
  • Use Case: When a Pull Request is submitted, this Skill can perform a thorough review, identifying potential security vulnerabilities, suggesting performance optimizations, and verifying test coverage, providing actionable feedback to the developer.

Quick Start

Use the review-code skill to perform a code review on the latest changes in the current repository.

Frequently Asked Questions about review-code

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

FAQPage Schema
How do I automate pull request code reviews?

Automate pull request code reviews by using AI agents that analyze codebase verification, API validation, and spec density. This Skill evaluates code quality, security, testing, performance, and documentation dimensions.

Can I perform security audits on Python and Rust codebases?

Yes, you can perform security audits on Python and Rust codebases. The review process supports multi-language checks for TypeScript, Python, Rust, and Go to identify potential vulnerabilities.

What is the best way to review project specifications and proposals?

Reviewing project specifications and proposals is best handled through research-grounded AI analysis that evaluates spec density and validates APIs against the codebase.

How are findings classified during an AI code review?

Findings during an AI code review are classified as BLOCKER, IMPROVEMENT, or PRAISE. This structured feedback provides clear evidence and actionable suggestions for developers.

Does the code review process use static checklists or dynamic research?

The code review process uses both dynamic research and multi-dimensional structured checklists. Opinions are backed by actual codebase searches and web research rather than just pre-existing AI knowledge.

How do I check test coverage and performance before merging a pull request?

Check test coverage and performance before merging by running an automated review that assesses code quality and testing dimensions. It provides structured feedback with evidence to verify coverage.