code-review

Review code diffs with four-perspective analysis and P1/P2/P3 severity triage.

Updated Apr 4, 2026
One-click install
npx skills add https://github.com/anionzo/skill --skill code-review-anionzo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/anionzo/skill/tree/main/skills/code-review
Command: npx skills add https://github.com/anionzo/skill --skill code-review-anionzo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides a structured, multi-perspective approach to code reviews, introducing risk-based triage and a verification gate to prevent incomplete or falsely claimed completions.

Core Features & Use Cases

  • Four-perspective evaluation (code quality, architecture, security, completeness) with severity triage (P1/P2/P3).
  • Supports both giving reviews and receiving feedback, including verification workflows and acceptance criteria checks.
  • Enables consistent, policy-driven review outcomes before commits, PRs, or handoffs.

Quick Start

Load this skill when you need to review changes, respond to feedback, or verify completion with the verification gate.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I perform a structured code review that covers security and architecture?

A structured code review evaluates diffs across four perspectives: code quality, architecture, security, and completeness. It assigns P1/P2/P3 severity levels to identified risks, ensuring feedback is comprehensive and prioritized before pull request approval.

What is risk-based triage in a pull request review process?

Risk-based triage in a pull request review process categorizes identified issues into P1, P2, and P3 severity levels. This triage prevents biased feedback by prioritizing critical security and architecture risks before a verification gate allows completion.

How do I verify completion and acceptance criteria when receiving third-party code review feedback?

Verifying completion when receiving third-party code review feedback requires passing a verification gate. This gate checks that all P1/P2/P3 severity issues are resolved and acceptance criteria are met before approving commits or handoffs.

Can I use multi-perspective code review for changes across multiple teams?

Yes, multi-perspective code review supports evaluating changes across teams. It applies a consistent, policy-driven evaluation framework with risk gates to ensure uniform quality-assurance outcomes during cross-team handoffs or pull requests.

What's the best way to prevent incomplete or biased feedback during a code review?

The best way to prevent incomplete or biased feedback during a code review is implementing a four-perspective analysis with risk-based triage. Categorizing findings into P1/P2/P3 severities forces comprehensive evaluation before a final verification gate permits completion.