skills.rest
heyu-ai
heyu-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

mob-code-review-only

Automate external PR code reviews using multi-model collaboration.

Updated May 15, 2026
Search Tags:#code review#feedback#PR review#multi-model collaboration#external PR
One-click install
npx skills add https://github.com/heyu-ai/yibi-stack --skill mob-code-review-only
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mob-code-review-only
Source: https://github.com/heyu-ai/yibi-stack/tree/main/plugins/pr-flow/skills/mob-code-review-only
Command: npx skills add https://github.com/heyu-ai/yibi-stack --skill mob-code-review-only

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pr-flow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the code review process for external PRs by leveraging multiple models for collaborative review, providing comprehensive feedback without altering the original code.

Core Features & Use Cases

  • Multi-Model Collaboration: Integrates Claude, Codex, and agy to perform independent reviews and debates, resulting in a robust and unbiased review.
  • Review-Only: Delivers feedback as suggestions only, preserving the original codebase and ensuring the reviewer's input is constructive.
  • Use Case: Ideal for reviewing a colleague's or external contributor's PR, ensuring that the codebase is of high quality and free of critical issues.

Quick Start

To initiate a code review for a specific PR, use the command: /mob-code-review-only #<PR number>

Frequently Asked Questions about mob-code-review-only

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

FAQPage Schema
How do I automate PR code review for external contributors without modifying the codebase?▼

You can automate external PR code review by deploying a multi-model collaboration workflow that analyzes the pull request and delivers constructive feedback as suggestions only, leaving the original codebase unmodified.

How does multi-model collaboration work for pull request reviews?▼

Multi-model collaboration for pull request reviews works by integrating Claude for coordination while utilizing Codex and agy to perform independent reviews and debates, resulting in robust and unbiased feedback for the PR.

What do I need to set up to run automated GitHub PR reviews with multiple models?▼

To run automated GitHub PR reviews with multiple models, you need to install the required pr-flow plugin and configure GitHub integration for PR handling before initiating the review process.

Can I use this multi-model approach to review a colleague's pull request?▼

Yes, you can use this multi-model approach to review a colleague's pull request, as it is specifically designed for reviewing external contributors' code while ensuring high quality and identifying critical issues.

What is the best way to get comprehensive feedback on an external PR?▼

The best way to get comprehensive feedback on an external PR is leveraging a review-only multi-model setup that performs independent reviews and debates, providing robust suggestions without altering the original code.

Does the automated code review process change the original pull request code?▼

No, the automated code review process does not change the original pull request code, as it operates in a review-only mode that delivers feedback as suggestions to preserve the original codebase.

Related Skills

Explore More Software Engineering Skills→
tile-aitile-ai
346

tilelang-github-operations

Install GitHub CLI and create pull requests via authenticated workflows.

Official
Advanced
becky3becky3
1

fix-reviews

Fetch unresolved GitHub pull request review comments and apply fixes.

Community
Advanced
RafayelGardishyanRafayelGardishyan

check

Run golangci-lint, Biome, and svelte-check quality checks before commits.

Community
Intermediate
Greenmamba29Greenmamba29

github-pr-reviewer

Review GitHub pull requests for code quality and security issues.

Community
Advanced