critique

Evaluate interface design quality with Nielsen heuristic scores and prioritized remediation commands.

Updated Jul 5, 2025
One-click install
npx skills add https://github.com/nsuberi/proto-portal-showcase-hub --skill critique-nsuberi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/nsuberi/proto-portal-showcase-hub/tree/main/apps/ai-builders-portal/.claude/skills/critique
Command: npx skills add https://github.com/nsuberi/proto-portal-showcase-hub --skill critique-nsuberi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides an expert, structured UX and visual design critique that surfaces whether an interface actually works for its users by evaluating visual hierarchy, information architecture, cognitive load, emotional journey, affordance, and accessibility. It helps teams move beyond vague feedback by producing quantified heuristic scores, persona-specific red flags, and prioritized, executable remediation steps.

Core Features & Use Cases

  • AI Slop Detection: Identifies common AI-generated anti-patterns (palette, glassmorphism, generic layouts) and flags when a design reads as machine-produced.
  • Heuristic Scoring & Cognitive Load: Runs Nielsen-style scoring across 10 heuristics and the 8-item cognitive load checklist, reporting counts and severity bands.
  • Persona-driven Failures & Prioritized Fixes: Produces persona-specific red flags (Alex, Jordan, Sam, etc.), a ranked list of P0–P3 issues, and maps each problem to concrete product commands to fix it.
  • Deliverables: Anti-patterns verdict (pass/fail), a filled heuristic table with scores, top 3–5 priority issues with fixes and suggested commands, minor observations, and targeted follow-up questions to set scope.

Quick Start

Ask critique to review the homepage hero (include a URL or screenshot), name the target user, and state the primary goal of that screen.

Frequently Asked Questions about critique

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

FAQPage Schema
How do I run a heuristic evaluation on a UI design?

To run a heuristic evaluation, submit a screenshot or URL of your interface to receive Nielsen-style heuristic scores across 10 usability heuristics. The evaluation generates quantified scores, cognitive load failure counts, and severity bands to identify exact design quality issues.

What is cognitive load in UX design and how is it measured?

Cognitive load in UX design refers to the mental effort required to use an interface, measured here via an 8-item cognitive load checklist. The evaluation reports failure counts and severity bands to highlight where visual hierarchy and information architecture overwhelm users.

How do I detect AI-generated design anti-patterns in my interface?

To detect AI-generated design anti-patterns, run an AI slop detection assessment that flags generic layouts, glassmorphism, and machine-produced palettes. The evaluation provides a pass or fail verdict on whether your interface reads as AI-generated.

Can I get persona-specific UX red flags for my prototype?

Yes, you can get persona-specific UX red flags by stating your target user and primary screen goal during the review. The evaluation produces targeted red flags for distinct personas and maps them to prioritized P0 through P3 remediation steps.

What is the best way to prioritize UI remediation fixes after a design critique?

The best way to prioritize UI remediation fixes is to use a ranked list of P0 to P3 issues mapped to concrete product commands. This approach transforms vague visual hierarchy and usability feedback into actionable, executable development tasks.

Does this UX critique work on individual components or full user flows?

This UX critique works on individual components, full user flows, screens, and prototypes. It evaluates visual hierarchy, information architecture, and emotional impact regardless of the scope you provide for the heuristic assessment.