pr-review

Classify PR review findings by severity tiers for merge decisions.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Kiwi-Home/ai-coding-resources --skill pr-review-kiwi-home
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pr-review
Source: https://github.com/Kiwi-Home/ai-coding-resources/tree/main/plugins/coding-workflows/skills/pr-review
Command: npx skills add https://github.com/Kiwi-Home/ai-coding-resources --skill pr-review-kiwi-home

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Framework for standardizing PR reviews with severity-tiered findings, authoritative criteria, and actionable follow-ups to improve code quality and governance.

Core Features & Use Cases

  • Severity Tiers: enforce a single tier per finding (MUST FIX, FIX NOW, CREATE ISSUE) to standardize triage.
  • Trivial Check & Review Category: provides decision frameworks to classify issues and guide actions.
  • CREATE ISSUE Protocol: a structured workflow to generate consolidated follow-up issues for non-blocking findings.
  • CLI/CI applicability: applicable to PR reviews from command-line or CI pipelines.

Quick Start

Issue a structured PR review workflow on a new PR to kick off governance checks.

Frequently Asked Questions about pr-review

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

FAQPage Schema
How do I standardize PR review findings with severity tiers to guide merge decisions?

Standardize PR review findings by classifying issues into severity tiers like MUST FIX, FIX NOW, and CREATE ISSUE to guide merge decisions. This framework applies strict scoring to triage code quality and governance in CLI or CI pipelines.

What is the structured workflow for triaging code review issues in continuous integration?

The structured workflow for triaging code review issues in continuous integration applies severity-tiered criteria to classify findings, enforce strict scoring, and generate consolidated follow-up issues for non-blocking findings.

Can I use severity-guided checks for multi-file projects in command-line workflows?

Yes, you can use severity-guided checks for multi-file projects in command-line workflows. The framework applies to code review workflows in both CLI and CI contexts, spanning single PRs and multi-file projects.

What's the best way to handle non-blocking findings during a code review?

The best way to handle non-blocking findings during a code review is using the CREATE ISSUE Protocol. This structured workflow generates consolidated follow-up issues to document actionable acceptance criteria without blocking merges.

How does the trivial check and review category framework classify code quality issues?

The trivial check and review category framework classifies code quality issues by enforcing a single severity tier per finding. This provides decision frameworks to categorize issues and guide actions for merge governance.