critique

Run two independent UX assessments and generate a combined critique report.

Updated Feb 21, 2026
One-click install
npx skills add https://github.com/byonk19-svg/rt-scheduler --skill critique-byonk19-svg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: critique
Source: https://github.com/byonk19-svg/rt-scheduler/tree/main/.cursor/skills/critique
Command: npx skills add https://github.com/byonk19-svg/rt-scheduler --skill critique-byonk19-svg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Evaluates interface designs to surface AI-generated design patterns and usability issues, enabling teams to improve clarity, consistency, and user satisfaction without manual bias.

Core Features & Use Cases

  • Two independent assessments: LLM review and automated detector results, synthesized into a combined critique.
  • Holistic UX scoring using Nielsen heuristics and a cognitive-load framework to identify prioritization and remediation paths.
  • Deliverables include a prioritized list of issues, actionable fixes, and device-agnostic recommendations for product, design, and engineering teams.
  • Use cases: evaluating dashboards, onboarding flows, and form wizards to ensure clarity, efficiency, and accessibility.

Quick Start

Run the critique workflow on the target design to obtain a unified 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 UX critique on web or mobile interface designs?

To run a UX critique, submit clear design prompts to trigger dual independent assessments. The workflow synthesizes an LLM review and automated detector results into a combined critique report with prioritized issues and actionable fixes.

What is AI slop detection in UX design assessments?

AI slop detection identifies AI-generated design patterns within interface artifacts. The critique workflow runs automated detectors alongside an LLM review to surface these generated patterns and usability issues, enabling teams to improve design clarity without manual bias.

How does cognitive load evaluation work for dashboard and onboarding flows?

Cognitive load evaluation assesses interfaces using a specialized framework to identify violations causing user friction. The critique workflow targets dashboards and onboarding flows, producing device-agnostic recommendations and prioritized remediation paths for engineering teams.

Can I use Nielsen heuristics to evaluate form wizards and accessibility?

Yes, the critique workflow applies Nielsen heuristics to evaluate form wizards and ensure accessibility. It generates a holistic UX score that identifies heuristic gaps, producing actionable fixes and device-agnostic recommendations for product, design, and engineering teams.

What do I need to ensure reproducible results from a design critique?

Reproducible design critique results require clear prompts, access to detection tooling, and a well-defined skill description. Providing these inputs allows the workflow to consistently evaluate UX artifacts and generate combined critique reports.