code-review-eval

Analyze code changes and generate a prioritized review report.

Updated Feb 28, 2026
One-click install
npx skills add https://github.com/cjohnhanson/codelikecody --skill code-review-eval
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review-eval
Source: https://github.com/cjohnhanson/codelikecody/tree/main/skills/code-review-eval
Command: npx skills add https://github.com/cjohnhanson/codelikecody --skill code-review-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structured code review is labor-intensive and error-prone; this skill orchestrates multi-pass evaluations to surface design, functionality, complexity, tests, naming, and SOLID/code-smell issues, delivering a single prioritized report.

Core Features & Use Cases

  • Multi-pass framework reviews that target design, functionality, complexity, tests, naming, and security considerations.
  • Generates a synthesized, prioritized report for code changes, PRs, or patch sets to accelerate quality gates.
  • Suitable for CI pipelines and manual reviews to improve consistency and defensibility of changes.

Quick Start

Analyze a code patch or PR to generate a prioritized quality report.

Frequently Asked Questions about code-review-eval

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

FAQPage Schema
How do I automate code review for pull requests?

Automated code review for pull requests analyzes patch sets to evaluate design, functionality, complexity, tests, and naming. It generates a single prioritized report aligned with Google's Review Priority Hierarchy and SOLID principles to accelerate quality gates.

What is framework-guided static analysis for code quality?

Framework-guided static analysis evaluates code changes through multiple passes targeting SOLID principles and code smells. It surfaces issues across design, functionality, complexity, tests, and naming categories, aggregating findings into a synthesized, prioritized report.

Can I use automated code review in a CI-CD pipeline?

Automated code review suits CI pipelines by generating prioritized quality reports for code changes and patch sets. This improves consistency and defensibility of changes while accelerating manual and automated quality gates.

How does multi-pass code review improve quality assurance?

Multi-pass code review improves quality assurance by systematically evaluating design, functionality, complexity, tests, naming, and security considerations. It aggregates findings into a prioritized report based on established review hierarchies and SOLID principles.

Does structured code review support multiple programming languages?

Structured code review supports pull requests, patch sets, and commits across multiple programming languages. It applies framework-guided evaluations to surface design and functionality issues regardless of the language used.

What is the best way to prioritize code review findings?

The best way to prioritize code review findings is aligning them with Google's Review Priority Hierarchy and SOLID principles. This approach categorizes issues by design, functionality, complexity, tests, and naming to produce a synthesized report.