Does this skill require external tools like Playwright?

While it can function using manual user observations, it is optimized for use with the Playwright MCP for automated browser walkthroughs and the Linear MCP for managing discovered issues.

What is the 'dogfood' mode in UX Evaluator?

Dogfood mode assesses production readiness by first simulating a real user journey to find friction points, then performing deep-dive technical and infrastructure audits to identify the root causes of those issues.

Can I use custom product context for evaluations?

Yes, the skill allows you to load product context from local markdown files or Linear documents, including details like value propositions, target personas, and core loops.

What kind of output does the UX Evaluator generate?

The skill produces timestamped markdown reports containing executive summaries, severity-rated findings, reproduction steps, and optional ASCII flow diagrams.

UX Evaluator

Name: UX Evaluator
Author: mberto10

bymberto10

0•

Security & Testing

Evaluates user experience, assesses production readiness, and identifies UI-to-backend gaps through structured auditing workflows.

The UX Evaluator skill provides a comprehensive framework for auditing digital products directly within Claude Code. It features three distinct modes: 'ux-eval' for lifecycle-based quality assessments, 'dogfood' for multi-layered production readiness checks (User, Tech, and Infra), and 'mcp-eval' for analyzing Model Context Protocol tool-to-widget chains. By integrating with Playwright for browser automation and Linear for issue tracking, it automates the discovery of friction points, technical bugs, and architectural inconsistencies, delivering structured markdown reports and actionable task lists that bridge the gap between design and implementation.

Key Features

01Multi-mode evaluation covering UX lifecycle, dogfooding, and MCP analysis.

02Detailed markdown report generation with severity ratings and reproduction steps.

03Integrated browser automation support via Playwright MCP for live flow analysis.

04Automated issue reporting with Linear project and ticket synchronization.

050 GitHub stars

06Multi-perspective auditing that separates user experience, code quality, and infrastructure.

Use Cases

01Performing a comprehensive UX audit before a major product launch or feature release.

02Evaluating the efficiency and conversational intent of MCP-based application interfaces.

03Identifying technical debt and UI-to-backend gaps during intensive dogfooding sessions.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add mberto10/mberto-compound ux-evaluator

For use in Claude.ai and ChatGPT

Key Features

01Multi-mode evaluation covering UX lifecycle, dogfooding, and MCP analysis.

02Detailed markdown report generation with severity ratings and reproduction steps.

03Integrated browser automation support via Playwright MCP for live flow analysis.

04Automated issue reporting with Linear project and ticket synchronization.

050 GitHub stars

06Multi-perspective auditing that separates user experience, code quality, and infrastructure.

Use Cases

01Performing a comprehensive UX audit before a major product launch or feature release.

02Evaluating the efficiency and conversational intent of MCP-based application interfaces.

03Identifying technical debt and UI-to-backend gaps during intensive dogfooding sessions.