critique

Score UI designs with Nielsen heuristics and prioritized severity issues.

Updated May 5, 2026
One-click install
npx skills add https://github.com/riabtsev/viscore_main --skill critique-riabtsev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/riabtsev/viscore_main/tree/main/.github/skills/critique
Command: npx skills add https://github.com/riabtsev/viscore_main --skill critique-riabtsev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps you evaluate whether a design truly works as an experience by exposing UX, hierarchy, cognitive load, and trust issues that can’t be found by technical checks alone.

Core Features & Use Cases

  • AI Slop Detection (anti-generic UX): Detects common “AI-generated” design fingerprints (palette, layout patterns, visual noise) and flags whether the UI looks fresh versus template-like.
  • UX Quality Scoring with UX Heuristics: Produces quantitative Nielsen-heuristics scoring plus an overall design health score.
  • Actionable, prioritized fixes: Turns findings into ranked severity issues (P0–P3) with concrete remediation guidance and suggested next commands.
  • Persona-based red-flag testing: Walks through likely failure modes for 2–3 relevant personas (e.g., power user, first-timer) with specific elements called out.

Quick Start

Use the critique skill to review a specific page or component by first loading the design context via the frontend-design protocol, then run a UX critique for the target area and return the prioritized issues and recommended fixes.

Frequently Asked Questions about critique

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

FAQPage Schema
How do I run a UX critique on a UI design to identify usability issues?

To run a UX critique, load your design context and target area, then evaluate visual hierarchy and information architecture. The process applies Nielsen heuristics to score usability, test failure modes against personas, and output prioritized severity issues with concrete remediation steps.

What is AI slop detection in UI design and how does it flag generic templates?

AI slop detection identifies template-like, AI-generated design fingerprints by analyzing palette choices, layout patterns, and visual noise. It flags whether a user interface looks fresh or suffers from generic anti-patterns, helping you eliminate visual sameness and improve distinctiveness.

Can I use Nielsen heuristics to score cognitive load and information architecture problems?

Yes, Nielsen heuristics are applied to score overall design health and quantify usability quality. The evaluation specifically includes executing a cognitive-load checklist and analyzing information architecture to expose hierarchy and trust issues that technical checks miss.

How do I test edge cases like empty, loading, and error states during a design review?

Testing edge cases involves reviewing empty, loading, and error states alongside onboarding, dashboards, and marketing flows. The critique applies persona-based red-flag testing to walk through likely failure modes for relevant personas, calling out specific problematic UI elements.

How do I prioritize UX design issues and get actionable fixes?

Prioritizing UX issues involves ranking findings by severity from P0 to P3. The critique outputs quantified scores alongside concrete remediation guidance and suggested next commands, turning design feedback into actionable, prioritized fixes for immediate implementation.

What is the best way to evaluate if a user interface works for different user personas?

Evaluating a interface for different users requires persona-based red-flag testing across 2-3 relevant personas like power users and first-timers. This approach walks through likely failure modes, calling out specific elements to ensure the design handles varying user needs and contexts.