Ux Design logo

Ux Design

Community
flitzrrr
ux-design

User research, interaction patterns, information architecture, and UX methods. Defines the five-plane model, user flows, UX laws, and validation methods for user-centered digital products.

Overview

Publisherflitzrrr
Repositoryfrontend-design-skills
Skill nameux-design
Stars
9
Forks
2
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Ux Design 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.
    https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/ux-design
  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/flitzrrr/frontend-design-skills.git /tmp/frontend-design-skills
mkdir -p .claude/skills
cp -r /tmp/frontend-design-skills/skills-src/ux-design .claude/skills/ux-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Design 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 Design 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 Design 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.

UX Design

Systematically designing user experiences -- from strategy to validated interaction.

Scope

Use this skill when: You are planning user research, creating personas, defining information architectures, documenting user flows, designing interaction patterns, or auditing existing products for UX quality.

Principles

1. The User Determines the Design -- Not the Designer

Every design decision is based on real user data. Assumptions without validation are speculation.

2. Design Experiences, Not Surfaces

UX encompasses the entire interaction -- from first perception to long-term usage.

3. Simplicity Beats Completeness

One feature that everyone understands is more valuable than ten features that nobody can find.

4. Emotions Are Measurable Success Factors

Positive experiences generate trust and return visits. UX is directly business-critical.

5. Iteration Over Perfection

Rapid prototyping, early testing, and continuous improvement beats extended planning phases.

Rules

The 5 Planes of User Experience (Garrett Model)

  • DO: Work from bottom to top: Strategy > Scope > Structure > Skeleton > Surface.
  • DO: At Plane 1 (Strategy), define: Who are the users? What are their goals? What are the business objectives?
  • DO: At Plane 2 (Scope), prioritize features by user need, not by stakeholder wishes.
  • DON'T: Jump directly to visual design (Plane 5) without defining the underlying planes.

User Research

  • DO: Conduct at least 5 user interviews or usability tests BEFORE design.
  • DO: Create data-driven personas: name, demographics, goals, pain points, context.
  • DO: Use empathy maps as a quick format: What does the user think, feel, say, and do?
  • DON'T: Create personas based on team assumptions. At least 3 real data points per persona.
  • DON'T: Test only with colleagues. Always test with the actual target audience.

Information Architecture (IA)

  • DO: Structure content according to the users' mental model, not the organizational structure.
  • DO: Conduct card sorting to validate the content structure.
  • DO: Keep navigation depth shallow: max. 3 clicks to reach target content.
  • DO: Label navigation items in user language, not in industry jargon.
  • DON'T: Use mega-menus with more than 7 main categories (Miller's Law: 7 +/- 2).

Interaction Design

  • DO: Provide immediate feedback on every action (max. 400ms without feedback).
  • DO: Make error handling helpful: WHAT went wrong and HOW to fix it.
  • DO: Provide undo capability for destructive actions (min. 5-second undo window).
  • DO: Reduce decisions per page (Hick's Law).
  • DON'T: Show error messages only after form submission. Inline validation is the standard.
  • DON'T: Use confirmation dialogs for trivial actions. Only for irreversible actions.

UX Laws

  • DO: Fitts' Law -- Touch targets at least 44x44px, close to the expected location.
  • DO: Jakob's Law -- Follow established conventions (users know other websites).
  • DO: Doherty Threshold -- System responses under 400ms feel instantaneous.
  • DO: Postel's Law -- Be liberal in what you accept, strict in what you produce.

User Flows

  • DO: Define the primary flow (happy path) + at least 2 alternative paths.
  • DO: Document flows as flowcharts with decision points.
  • DO: Validate flows with real users before creating wireframes.
  • DON'T: Create flows that lead to dead ends (pages without a next action or a way back).

Patterns

Detailed pattern descriptions: see references/patterns.md

Progressive Disclosure

Show only the essentials at the first level. Details behind "Learn more." Multi-step forms instead of one long form.

Onboarding Flow

Max. 3-5 steps. Progress indicator visible. Skip option. After completion: direct access to core value.

Search-Centric Design

Prominent search bar. Autocomplete with instant results. Filter options. Zero-results page with alternatives.

Feedback Loop

Visual feedback (hover, active), system feedback (loading indicator), result feedback (success message).

Empty States

Never leave blank areas. Always: explanation + call to action + appropriate visual.

Anti-Patterns

Feature Creep

Ever more features without validation. Solution: Every feature needs validated user demand. Under 20% usage = remove or hide.

Assumption-Driven Design

"I think the user wants..." Solution: At least 3 data points per key decision.

The Happy Path Only

Designing only for the ideal case. Solution: Define and design at least 3 error scenarios per flow.

Cognitive Overload

Too many options per page. Solution: Miller's Law (7 +/- 2). One page = one primary goal.

Ignoring Context

Same UX across all devices. Solution: Design context-dependently (mobile: on the go, one hand; desktop: more attention).

Checklist

  • Strategy plane defined: user goals and business objectives documented?
  • At least 3 data-driven personas created?
  • User flows documented (happy path + edge cases)?
  • Information architecture validated (card sorting or tree testing)?
  • Navigation labels in user language (no internal jargon)?
  • Navigation depth max. 3 levels?
  • Immediate feedback on every action (under 400ms)?
  • Error handling helpful (WHAT + HOW)?
  • Undo for destructive actions?
  • Inline validation on forms?
  • Empty states with explanation and call to action?
  • Touch targets at least 44x44px?
  • Max. 7 main navigation items?
  • No feature without validated user demand?

Cross-References

  • ui-design -- Visual implementation of UX concepts
  • accessibility -- Inclusive design as a UX cornerstone
  • usability -- Testing methods and heuristics
  • navigation-design -- IA implementation in navigation structures
  • customer-journey -- UX in the overall context of the user journey
  • design-process -- UX methods in the project workflow
  • landing-pages -- Conversion-optimized UX patterns

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 Design AI skill do?

User research, interaction patterns, information architecture, and UX methods. Defines the five-plane model, user flows, UX laws, and validation methods for user-centered digital products.

Why use Ux Design on TypingMind?

Because you install it once and use it with any model. Ux Design 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 Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/ux-design. 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 Design?

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 Design?

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

Is the Ux Design AI skill free?

Yes. It is published on GitHub by flitzrrr under the MIT license. 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 👇