skills.rest
qazz92
qazz92COMMUNITY
Explore all skills by this author →
GitHub

review

Automate code reviews for correctness, security, quality, performance, and test coverage.

Updated May 15, 2026
Search Tags:#quality assurance#code review#pull request#LLM#automated review
One-click install
npx skills add https://github.com/qazz92/glm-code --skill review-qazz92
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/qazz92/glm-code/tree/main/packages/core/src/skills/bundled/review
Command: npx skills add https://github.com/qazz92/glm-code --skill review-qazz92

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates code reviews to identify issues in correctness, security, code quality, performance, and test coverage, streamlining the process and enhancing the accuracy of reviews.

Core Features & Use Cases

  • Parallel Multi-Dimensional Review: Simultaneously reviews multiple aspects of code (correctness, security, code quality, performance, test coverage) with parallelized agents.
  • Deduplication & Verification: Removes duplicate findings and verifies the accuracy of identified issues, ensuring high confidence in results.
  • Iterative Reverse Audit: Continuously refines the review by identifying missed issues in subsequent rounds, leading to a more comprehensive review.
  • Use Case: For a large codebase with frequent pull requests, this Skill can be used to automate the review process, significantly reducing the time required for manual code reviews and increasing the consistency and reliability of the reviews.

Quick Start

To review a pull request, use the review skill with the following command: /review <pr-number> or /review <file-path>.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate code reviews for pull requests?▼

Automate code reviews by running parallel agents to analyze pull requests, detecting issues in security, performance, and test coverage. Use the command /review <pr-number> or /review <file-path> to initiate the automated review process.

How does automated code review handle duplicate findings?▼

Automated code review handles duplicate findings through a verification process that removes duplicates and verifies identified issues. This ensures high confidence in the final review results.

Does automated code review work for large codebases with frequent pull requests?▼

Automated code review works for large codebases with frequent pull requests by streamlining the review process. It significantly reduces manual review time while increasing consistency and reliability across all codebase maintenance workflows.

Can I review code quality and security simultaneously?▼

You can review code quality and security simultaneously using parallel multi-dimensional review. This approach concurrently analyzes correctness, security, performance, and test coverage to provide comprehensive feedback.

How does an LLM identify missed issues during code review?▼

An LLM identifies missed issues through iterative reverse audit, continuously refining the code review in subsequent rounds. This process ensures a more comprehensive review by catching overlooked problems.

What do I need to run automated codebase maintenance and quality assurance?▼

You need access to the codebase and a suitable LLM to run automated codebase maintenance and quality assurance. These prerequisites enable the system to analyze code and generate accurate review feedback.

Related Skills

Explore More Software Engineering Skills→
awinogradovawinogradov
5

pr:resolve

Analyze pull request comments, apply code fixes, and reply to reviewers via GitHub API.

Community
Advanced
an8079an8079
4

auto-critique

Automate code review for quality, correctness, security, and performance.

Community
Advanced
getsentrygetsentry
216

review

Automate inspection and validation of code fixtures and project data structures.

Official
Basic
OneWave-AIOneWave-AI
245

code-review-pro

Review code for security vulnerabilities, performance bottlenecks, and maintainability issues.

Official
Basic