critique

Run dual LLM and automated UX assessments to produce a combined critique report.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/nitipoomph-coder/Project_phase1 --skill critique-nitipoomph-coder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/nitipoomph-coder/Project_phase1/tree/main/.gemini/critique
Command: npx skills add https://github.com/nitipoomph-coder/Project_phase1 --skill critique-nitipoomph-coder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Evaluate design quality from a UX perspective using a structured, dual-assessment workflow to surface actionable feedback across visual hierarchy, information architecture, cognitive load, and emotional impact.

Core Features & Use Cases

  • Dual assessment workflow: an LLM-based design review plus automated detection to provide complementary perspectives.
  • Combined critique report: a synthesized output including AI slop verdict, heuristic scores, cognitive load findings, and prioritized issues.
  • Output versatility: generates a design health score, actionable recommendations, and persona-based red flags for stakeholders.

Quick Start

Run the full critique on the current design by executing both the LLM review and the automated detector, then compile the combined report.

Frequently Asked Questions about critique

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

FAQPage Schema
How do I run a structured UX critique on a web interface?

A structured UX critique evaluates visual hierarchy, information architecture, and cognitive load by running a dual-assessment workflow on your design artifacts to produce a combined report with heuristic scores and prioritized improvements.

What is cognitive load evaluation in a design review?

Cognitive load evaluation in a design review assesses how much mental effort users expend when processing an interface, surfacing findings within a combined critique report to identify red flags and prioritize UX improvements.

Does this UX critique provide Nielsen heuristic scores for mobile apps?

Yes, the UX critique evaluates mobile apps and generates a combined report that includes a Nielsen heuristic score, an AI slop verdict, and persona-based red flags to measure design health.

Can I critique a component library without external dependencies?

Yes, you can critique component libraries without external dependencies by executing the built-in LLM design review and automated detector to evaluate visual hierarchy and information architecture.

What is the AI slop verdict in automated design feedback?

The AI slop verdict in automated design feedback identifies low-quality or generic AI-generated interface patterns by running an automated detector alongside an LLM design review to surface a combined critique.

What's the best way to evaluate emotional impact and visual hierarchy?

The best way to evaluate emotional impact and visual hierarchy is a dual-assessment workflow that synthesizes an LLM design review with automated detection to produce actionable recommendations.