critique

Assess code quality across five rubric dimensions and return a structured report.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/smallorbit/smallorbit-plugins --skill critique-smallorbit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/smallorbit/smallorbit-plugins/tree/main/plugins/polishkit/skills/critique
Command: npx skills add https://github.com/smallorbit/smallorbit-plugins --skill critique-smallorbit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Code reviews often rely on subjective impressions. This skill provides a structured, objective assessment of code quality, architecture, and readability, helping teams surface strengths and actionable improvements.

Core Features & Use Cases

  • Structured five-dimension rubric assessing Architecture & Separation of Concerns, Naming & Readability, Algorithmic Elegance, Testability & Design, and Idiomatic Consistency.
  • Produces a prioritized report with highlights, violation flags, and concrete remediation guidance suitable for PR discussions.
  • Works on single files, modules, or full repositories across languages and paradigms, aligning with common engineering practices.

Quick Start

Analyze a target codebase for architectural boundaries and readability and return a concise five-dimension report.

Frequently Asked Questions about critique

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

FAQPage Schema
How do I get a structured code quality assessment for a pull request?

A structured code quality assessment scores five dimensions—Architecture, Readability, Algorithmic Elegance, Testability, and Idiomatic Consistency—to provide objective PR feedback. It analyzes files or repositories and returns a rubric-based report with strengths and remediation steps.

What is the best way to review code architecture and readability objectively?

Reviewing code architecture and readability objectively requires a structured rubric that evaluates separation of concerns and naming conventions without subjective bias. This approach surfaces specific strengths and concrete remediation steps suitable for team discussions.

Can I run a code quality review on an entire repository or just single files?

You can run a code quality review on single files, modules, or entire repositories. The assessment adapts to the provided codebase scope and returns a consistent five-dimension quality report across different languages and paradigms.

How does a rubric-based code review report help with post-merge audits?

A rubric-based code review report helps with post-merge audits by providing a structured, historical record of architectural and design quality scores. It highlights violations and tracks concrete remediation guidance for future reference.

What dimensions are evaluated in an automated software engineering quality assessment?

An automated software engineering quality assessment evaluates five dimensions: Architecture and Separation of Concerns, Naming and Readability, Algorithmic Elegance, Testability and Design, and Idiomatic Consistency. Each dimension receives a score with actionable remediation guidance.