Ux Audit logo

Ux Audit

Community
viralcode
ux-audit

AI skill for automated design audits. Evaluate interfaces against proven UX principles for visual hierarchy, accessibility, cognitive load, navigation, and more. Based on Making UX Decisions by Tommy Geoco.

Overview

Publisherviralcode
Repositoryopenwhale
Skill nameux-audit
Stars
65
Forks
11
Bundled files
20
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 20 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by viralcode on GitHub. Read the source before you install it.

Installation

Install the Ux Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/viralcode/openwhale.git /tmp/openwhale
mkdir -p .claude/skills
cp -r /tmp/openwhale/skills/ux-audit .claude/skills/ux-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ux Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ux Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Design Audit Skill

Evaluate interfaces against proven UX principles. Based on Making UX Decisions by Tommy Geoco.

When to Use This Skill

  • Making UI/UX design decisions under time pressure
  • Evaluating design trade-offs with business context
  • Choosing appropriate UI patterns for specific problems
  • Reviewing designs for completeness and quality
  • Structuring design thinking for new interfaces

Core Philosophy

Speed ≠ Recklessness. Designing quickly is not automatically reckless. Recklessly designing quickly is reckless. The difference is intentionality.

The 3 Pillars of Warp-Speed Decisioning

  1. Scaffolding — Rules you use to automate recurring decisions
  2. Decisioning — Process you use for making new decisions
  3. Crafting — Checklists you use for executing decisions

Quick Reference Structure

Foundational Frameworks

  • references/00-core-framework.md — 3 pillars, decisioning workflow, macro bets
  • references/01-anchors.md — 7 foundational mindsets for design resilience
  • references/02-information-scaffold.md — Psychology, economics, accessibility, defaults

Checklists (Execution)

  • references/10-checklist-new-interfaces.md — 6-step process for designing new interfaces
  • references/11-checklist-fidelity.md — Component states, interactions, scalability, feedback
  • references/12-checklist-visual-style.md — Spacing, color, elevation, typography, motion
  • references/13-checklist-innovation.md — 5 levels of originality spectrum

Patterns (Reusable Solutions)

  • references/20-patterns-chunking.md — Cards, tabs, accordions, pagination, carousels
  • references/21-patterns-progressive-disclosure.md — Tooltips, popovers, drawers, modals
  • references/22-patterns-cognitive-load.md — Steppers, wizards, minimalist nav, simplified forms
  • references/23-patterns-visual-hierarchy.md — Typography, color, whitespace, size, proximity
  • references/24-patterns-social-proof.md — Testimonials, UGC, badges, social integration
  • references/25-patterns-feedback.md — Progress bars, notifications, validation, contextual help
  • references/26-patterns-error-handling.md — Form validation, undo/redo, dialogs, autosave
  • references/27-patterns-accessibility.md — Keyboard nav, ARIA, alt text, contrast, zoom
  • references/28-patterns-personalization.md — Dashboards, adaptive content, preferences, l10n
  • references/29-patterns-onboarding.md — Tours, contextual tips, tutorials, checklists
  • references/30-patterns-information.md — Breadcrumbs, sitemaps, tagging, faceted search
  • references/31-patterns-navigation.md — Priority nav, off-canvas, sticky, bottom nav

Usage Instructions

For Design Decisions

  1. Read 00-core-framework.md for the decisioning workflow
  2. Identify if this is a recurring decision (use scaffold) or new decision (use process)
  3. Apply the 3-step weighing: institutional knowledge → user familiarity → research

For New Interfaces

  1. Follow the 6-step checklist in 10-checklist-new-interfaces.md
  2. Reference relevant pattern files for specific UI components
  3. Use fidelity and visual style checklists to enhance quality

For Pattern Selection

  1. Identify the core problem (chunking, disclosure, cognitive load, etc.)
  2. Load the relevant pattern reference
  3. Evaluate benefits, use cases, psychological principles, and implementation guidelines

Decision Workflow Summary

When facing a UI decision:

1. WEIGH INFORMATION
   ├─ What does institutional knowledge say? (existing patterns, brand, tech constraints)
   ├─ What are users familiar with? (conventions, competitor patterns)
   └─ What does research say? (user testing, analytics, studies)

2. NARROW OPTIONS
   ├─ Eliminate what conflicts with constraints
   ├─ Prioritize what aligns with macro bets
   └─ Choose based on JTBD support

3. EXECUTE
   └─ Apply relevant checklist + patterns

Macro Bet Categories

Companies win through one or more of:

BetDescriptionDesign Implication
VelocityFeatures to market fasterReuse patterns, find metaphors in other markets
EfficiencyManage waste betterDesign systems, reduce WIP
AccuracyBe right more oftenStronger research, instrumentation
InnovationDiscover untapped potentialNovel patterns, cross-domain inspiration

Always align micro design bets with company macro bets.

Key Principle: Good Design Decisions Are Relative

A design decision is "good" when it:

  • Supports the product's jobs-to-be-done
  • Aligns with company macro bets
  • Respects constraints (time, tech, team)
  • Balances user familiarity with differentiation needs

There is no universally correct UI solution—only contextually appropriate ones.


Generating Audit Reports

When asked to audit a design, generate a comprehensive report. Always include these sections:

Required Sections (always include)

  1. Visual Hierarchy — Headings, CTAs, grouping, reading flow, type scale, color hierarchy, whitespace
  2. Visual Style — Spacing consistency, color usage, elevation/depth, typography, motion/animation
  3. Accessibility — Keyboard navigation, focus states, contrast ratios, screen reader support, touch targets

Contextual Sections (include when relevant)

  1. Navigation — For multi-page apps: wayfinding, breadcrumbs, menu structure, information architecture
  2. Usability — For interactive flows: discoverability, feedback, error handling, cognitive load
  3. Onboarding — For new user experiences: first-run, tutorials, progressive disclosure
  4. Social Proof — For landing/marketing pages: testimonials, trust signals, social integration
  5. Forms — For data entry: labels, validation, error messages, field types

Audit Output Format

json
{
  "title": "Design Name — Screen/Flow",
  "project": "Project Name",
  "date": "YYYY-MM-DD",
  "figma_url": "optional",
  "screenshot_url": "optional - URL to screenshot",
  
  "macro_bets": [
    { "category": "velocity|efficiency|accuracy|innovation", "description": "...", "alignment": "strong|moderate|weak" }
  ],
  
  "jtbd": [
    { "user": "User Type", "situation": "context without 'When'", "motivation": "goal without 'I want to'", "outcome": "benefit without 'so I can'" }
  ],
  
  "visual_hierarchy": {
    "title": "Visual Hierarchy",
    "checks": [
      { "label": "Check name", "status": "pass|warn|fail|na", "notes": "Details" }
    ]
  },
  "visual_style": { ... },
  "accessibility": { ... },
  
  "priority_fixes": [
    { "rank": 1, "title": "Fix title", "description": "What and why", "framework_reference": "XX-filename.md → Section Name" }
  ],
  
  "notes": "Optional overall observations"
}

Checks Per Section (aim for 6-10 each)

Visual Hierarchy: heading distinction, primary action clarity, grouping/proximity, reading flow, type scale, color hierarchy, whitespace usage, visual weight balance

Visual Style: spacing consistency, color palette adherence, elevation/shadows, typography system, border/radius consistency, icon style, motion principles

Accessibility: keyboard operability, visible focus, color contrast (4.5:1), touch targets (44px), alt text, semantic markup, reduced motion support

Navigation: clear current location, predictable menu behavior, breadcrumb presence, search accessibility, mobile navigation pattern

Usability: feature discoverability, feedback on actions, error prevention, recovery options, cognitive load management, loading states

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ux Audit AI skill do?

AI skill for automated design audits. Evaluate interfaces against proven UX principles for visual hierarchy, accessibility, cognitive load, navigation, and more. Based on Making UX Decisions by Tommy Geoco.

Why use Ux Audit on TypingMind?

Because you install it once and use it with any model. Ux Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ux Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/viralcode/openwhale/tree/main/skills/ux-audit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ux Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ux Audit?

As many as you like. As long as a model supports skills, you can use Ux Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ux Audit AI skill free?

It is published on GitHub by viralcode. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇