evaluate

Diagnoses UX issues through heuristic evaluations, cognitive walkthroughs, and anti-pattern detection with prioritized routing.

Updated Aug 26, 2026
One-click install
npx skills add https://github.com/danieliudi/trackforge-os --skill evaluate-danieliudi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evaluate
Source: https://github.com/danieliudi/trackforge-os/tree/main/.cursor/skills/evaluate
Command: npx skills add https://github.com/danieliudi/trackforge-os --skill evaluate-danieliudi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Design reviews often produce vague feedback like "the navigation feels off" without actionable next steps. This Skill runs structured UX evaluations that score findings, categorize issues by severity, and map every problem to the specific remediation skill that owns the fix. ## Core Features & Use Cases - Heuristic Evaluation: Applies Nielsen's 10 usability heuristics with a 0-4 severity scale and documented evidence for each violation. - Cognitive Walkthroughs: Walks every task step through four questions (motivation, visibility, understanding, feedback) to locate exact failure points. - Anti-Pattern Detection: Scans for dark patterns like confirmshaming, prechecked consent, and fake urgency, with severity classification and regulatory risk notes. - Use Case: Before launching a new checkout flow, run an evaluation to get a UX health score, a prioritized P0-P3 issue list, and a remediation roadmap routing each issue to the right specialist skill. ## Quick Start Evaluate the signup flow of my web app and give me a scored list of usability issues with recommended fixes.

Frequently Asked Questions about evaluate

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

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

Heuristic evaluation examines your interface against Nielsen's 10 usability heuristics, scoring each from 0 (no issues) to 4 (catastrophic). Each violation is documented with its location, user impact, and evidence, then routed to the appropriate remediation approach.

What is a cognitive walkthrough in UX evaluation?

A cognitive walkthrough steps through each task asking four questions: will the user know to act, notice the action, understand what it does, and see feedback. Steps with two or more failures are rated as likely abandonment points.

How are dark patterns detected and classified?

The evaluation scans for deceptive patterns like confirmshaming, prechecked consent, fake urgency, and hidden costs. Each is classified as Critical, High, Medium, or Low severity, with notes on regulatory implications such as GDPR or FTC guidelines.

Does this evaluation fix the UX issues it finds?

No, it diagnoses and routes issues rather than fixing them. Every finding maps to a specialist skill such as /fortify for edge cases, /articulate for copy problems, or /include for accessibility, producing a prioritized remediation roadmap.

When should I use a UX audit versus user research?

Use this evaluation when you need an expert assessment of an existing design against established heuristics and patterns. When findings raise questions only real users can answer, the evaluation routes to research planning instead.