pr-reviewer

2 forks
89
B

Comprehensive GitHub Pull Request code review skill. Use when asked to "review this PR", "code review", "review pull request", "check this PR", or when a GitHub PR URL is provided. Fetches PR metadata, diff, comments, commits, and related issues using gh CLI. Creates organized review workspace, analyzes code against industry-standard criteria, and optionally adds inline comments to the PR.

#review#code review#Pull Request#Reference#review pull#comments#review criteria#Pull

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install SpillwaveSolutions/pr-reviewer-skill/pr-reviewer
skilz install SpillwaveSolutions/pr-reviewer-skill/pr-reviewer --agent opencode
skilz install SpillwaveSolutions/pr-reviewer-skill/pr-reviewer --agent codex
skilz install SpillwaveSolutions/pr-reviewer-skill/pr-reviewer --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/SpillwaveSolutions/pr-reviewer-skill
2. Copy the agent skill directory:
cp -r pr-reviewer-skill ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Forks
2
Type
Non-Technical
Meta-Domain
general
Primary Domain
general
Sub-Domain
github review code review
Market Score
89

Agent Skill Grade

B
Score: 89/100 Click to see breakdown

Score Breakdown

Spec Compliance
14/15
PDA Architecture
26/30
Ease of Use
22/25
Writing Style
8/10
Utility
18/20
Modifiers: +1

Areas to Improve

  • Missing TOC in large reference files
  • Workflow steps 2-3 unclear boundary
  • Second-person usage in Tips section

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-19

Developer Feedback

I took a look at your pr-reviewer skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 89/100, solid B-grade territory. This is graded against Anthropic's best practices for Claude Code skills. Your spec compliance is chef's kiss (14/15), but you're losing points on Progressive Disclosure Architecture and a couple of workflow clarity issues that are totally fixable.

What's Working Well

  • Solid reference architecture – You've got 4 separate reference files (review criteria, GitHub CLI guide, scenarios, troubleshooting) layered one level deep from the main SKILL.md. That's the right call for keeping things organized.
  • Comprehensive trigger coverage – Your triggers are specific ("review pr", "code review", "check pr") and include the GitHub PR URL pattern (github.com/*/pull/*), which means this skill activates exactly when someone needs it.
  • Two-stage approval workflow – The /send and /send-decline approach prevents accidental posts to GitHub. That's a real safety feature that matters.
  • Clear review criteria checklist – The security/testing/maintainability/performance framework gives reviewers a systematic way to approach PRs instead of ad-hoc feedback.

The Big One: Missing TOC in Large Reference Files

Your references/review_criteria.md is 346 lines without a table of contents. That's a Progressive Disclosure problem – someone loading that file has no way to scan and jump to what they need. This is costing you 1 point.

Quick fix: Add a TOC after the title in references/review_criteria.md and any reference file over 100 lines:

# Code Review Criteria

## Table of Contents
- [Functionality and Correctness](#1-functionality-and-correctness)
- [Readability and Maintainability](#2-readabili...

AI-Detected Topics

Extracted using NLP analysis

review code review Pull Request Reference review pull comments review criteria Pull inline comments Request

Report Security Issue

Found a security vulnerability in this agent skill?