cursor-review

Automate Cursor Bugbot-style code reviews with Claude CLI agents.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/mataanin/multi-llm --skill cursor-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cursor-review
Source: https://github.com/mataanin/multi-llm/tree/main/skills/cursor-review
Command: npx skills add https://github.com/mataanin/multi-llm --skill cursor-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables automated, Bugbot-style code reviews using Claude CLI agents to standardize feedback, reduce manual effort, and speed up code quality assessment.

Core Features & Use Cases

  • Automated Cursor Bugbot-style code reviews via the cursor-review.sh script.
  • Review by commit, by branch, or by commit range with descriptive change notes guiding the process.
  • Structured feedback aligned with project conventions and quality gates, suitable for CI or local workflows.

Quick Start

Describe the changes you want reviewed and run the script to start the Bugbot-style review.

Frequently Asked Questions about cursor-review

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

FAQPage Schema
How do I automate code reviews using Claude CLI agents?

You can automate code reviews using Claude CLI agents by running a script that applies Bugbot-style reviews to your current branches, specific commits, or commit ranges with descriptive change notes guiding the process.

Can I run Cursor Bugbot-style code reviews in a CI pipeline?

Yes, Cursor Bugbot-style code reviews can run in CI pipelines. The review script provides integration steps and structured feedback aligned with project conventions, making it suitable for both local workflows and CI environments.

What is the best way to review specific commits in a local development environment?

The best way to review specific commits locally is to use an automated script that targets single commits or commit ranges, using descriptive change notes to guide the Claude CLI agent through the review.

Does the automated code review script work without external dependencies?

Yes, the automated code review script operates without external dependencies. It contains the prompt, validation logic, and integration steps needed to run Bugbot-style reviews using Claude CLI directly.

How do I guide the code review process for my current branch?

You guide the code review process for your current branch by providing descriptive change notes before running the script, which standardizes feedback and aligns the review with your project conventions.