PR Review

Analyze open pull requests and produce severity-tagged findings with inline comments.

Updated Jun 2, 2026

Search Tags:#automation #workflow #commenting #code-review #pull-requests #pr-review

Ready to run

npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill pr-review-atrium-hermes

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: PR Review
Source: https://github.com/Atrium-Hermes/atrium-lighthouse/tree/main/skills/pr-review
Command: npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill pr-review-atrium-hermes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual PR reviews are time-consuming and error-prone. This skill automates the process by producing severity-tagged findings, inline comments, and a concise verdict, freeing engineers to focus on high-impact issues.

Core Features & Use Cases

Fetches open PRs and applies skip rules to filter out drafts, bots, and trivial changes.
Analyzes PR diffs and contexts to generate precise, line-specific findings with severity tags, and posts an aggregated verdict.
Supports automated reviews across multiple repositories and integrates with memory/logs for dedup and traceability.

Quick Start

Run the PR review workflow against your repository's open PRs to generate severity-tagged findings and a final verdict.

Frequently Asked Questions about PR Review

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

FAQPage Schema

How do I automate code review for open pull requests?▼

Automated PR review works by fetching open pull requests, filtering out drafts and bots via skip rules, and analyzing diffs to produce severity-tagged inline comments and a final one-line verdict for consistent code governance.

What is the best way to filter out draft PRs and bots from automated pull request reviews?▼

The best way to filter noisy pull requests is using built-in skip rules that exclude drafts, bots, and trivial changes before analysis. This ensures automated reviews focus only on meaningful code changes across your repositories.

Can I run automated code reviews across multiple repositories?▼

Yes, you can run automated code reviews across multiple repositories. The skill supports automated governance over code changes in multiple repos and integrates with memory and logs for deduplication and traceability of findings.

How does the severity tagging work for inline code review comments?▼

Severity tagging assigns priority levels to specific findings within the PR diff context. The skill generates precise, line-specific findings with these severity tags, posts inline comments, and aggregates them into a final verdict.

When should I not use automated PR review for my code changes?▼

You should not use automated PR review for draft pull requests, bot-generated changes, or trivial modifications. The skill applies skip rules to bypass these noisy PRs, ensuring automated governance targets substantive code diffs only.