critique

Evaluate UI designs with an LLM critique and automated detection pass.

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/serguei9090/Agentic-Governance-Framework --skill critique-serguei9090
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/serguei9090/Agentic-Governance-Framework/tree/main/MasterPrompts/.agents/skills/critique
Command: npx skills add https://github.com/serguei9090/Agentic-Governance-Framework --skill critique-serguei9090

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

Core Features & Use Cases

  • Dual assessment: an LLM-based critique plus an automated detector pass to surface both qualitative and deterministic findings.
  • Structured critique output: health score, heuristic ratings, key issues, actionable recommendations, and prioritized fixes.
  • Use Case: Evaluate a dashboard prototype to generate recommendations for improving navigation, clarity, and accessibility.

Quick Start

Run the critique workflow on the target UI design artifact to obtain a combined health score, heuristic ratings, and prioritized remediation steps.

Frequently Asked Questions about critique

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

FAQPage Schema
How do I evaluate a UI design for usability risks and cognitive load?

To evaluate a UI design for usability risks, the workflow executes a dual assessment combining an LLM-based critique with automated detection. It produces a combined health score, heuristic ratings, and prioritized remediation steps to improve usability and consistency.

What is the best way to critique a dashboard prototype and get actionable UX feedback?

The best way to critique a dashboard prototype is applying a dual assessment workflow that generates heuristic ratings, issue lists, and prioritized remediation guidance. It delivers actionable recommendations as concrete commands or steps for designers and developers.

Can I get quantitative UX scores for visual hierarchy and information architecture?

Yes, you can get quantitative UX scores for visual hierarchy and information architecture. The assessment evaluates design quality with a structured health score, heuristic ratings, and automated anti-pattern detection to surface both qualitative and deterministic findings.

How does automated anti-pattern detection work for UI components?

Automated anti-pattern detection works by running a deterministic detector pass alongside an LLM-based critique on UI artifacts. This dual workflow surfaces specific design quality risks related to cognitive load, accessibility, and usability that might be missed by qualitative review alone.

Does this UX critique workflow require any specific design file formats or dependencies?

No specific dependencies are required to run the UX critique workflow. It is designed to apply to UI artifacts such as dashboards, product pages, or prototypes and evaluate them directly to produce actionable feedback and remediation guidance.

When should I not use an automated heuristic evaluation for my product design?

You should reconsider automated heuristic evaluation if your UI artifact is entirely non-visual or lacks interactive navigation, as the workflow specifically targets visual hierarchy, information architecture, and cognitive load within tangible product designs.