Skip to main content
ClaudeWave
Skill300 repo starsupdated yesterday

super-ui-ux-design

This Claude Code skill provides a comprehensive UI/UX design framework combining design theory (UX laws, Nielsen heuristics, visual hierarchy, typography, WCAG accessibility, design systems) with practical execution guidance for building production-grade interfaces. Use it when designing or rebuilding user interfaces across any medium, reviewing design work against usability principles, diagnosing conversion or adoption problems, or grounding visual decisions in evidence-based UX rather than aesthetic convention.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas /tmp/super-ui-ux-design && cp -r /tmp/super-ui-ux-design/.claude/skills/super-ui-ux-design ~/.claude/skills/super-ui-ux-design
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# 📐 The Full Schemata of UI/UX Design

> A wiki-style knowledge map. Each section is a node. Follow the links, build the schema in your head, then go break it against real users.
>
> **Format notes:** Internal links like [Visual Hierarchy](#-visual-hierarchy) jump between nodes. Mermaid blocks render in Obsidian, GitHub, Notion, and most modern markdown viewers.

---

## 🗺️ The Master Map

Start here. Everything below hangs off this tree.

```mermaid
mindmap
  root((DESIGN))
    Problem Solving
      Define the problem
      Constraints
      Trade-offs
      Iteration
    UX["UX (Experience)"]
      Research
      Information Architecture
      Interaction Design
      Usability
      Mental Models
      UX Laws & Heuristics
    UI["UI (Interface)"]
      Visual Hierarchy
      Layout & Grids
      Typography
      Color & Contrast
      Components
    Design Systems
      Tokens
      Components
      Patterns
      Documentation
    Business Layer
      Conversion
      Retention
      Trust & Credibility
      Aesthetics vs Performance
    Learning Layer
      Constructivism
      Schemata
      Mental Models
      Jakob's Law
```

---

## 🧩 Node 0 — What Is Design?

**Definition:** Design is the intentional shaping of something (a product, a screen, a service, a process) to achieve a purpose under constraints.

The keyword is *intentional*. Decoration happens to look nice. Design exists to *do* something.

Herbert Simon, in *The Sciences of the Artificial*, framed it roughly as: anyone who devises a course of action to change an existing situation into a preferred one is designing. By that definition, a doctor writing a treatment plan is designing. So is an engineer, a teacher, and yes, the person arranging buttons on a checkout page.

**So... is design about problem solving?**

Yes, with one important nuance.

Design *is* problem solving, but it's a specific flavor of it. Most design problems are what theorists call **wicked problems** (Rittel & Webber, 1973):

- There is no single correct answer, only better and worse ones
- The problem definition itself shifts as you work on it
- Every solution creates new constraints
- You can't fully test a solution without shipping it

This is why design is iterative by nature. You don't "solve" a checkout flow the way you solve a math equation. You propose, test, learn, and revise.

```mermaid
flowchart LR
    A[Existing Situation] -->|"Understand the problem"| B[Problem Definition]
    B -->|"Generate options"| C[Proposed Solution]
    C -->|"Test with reality"| D{Did it work?}
    D -->|"No / Partially"| B
    D -->|"Yes"| E[Preferred Situation]
    E -.->|"World changes, new problems"| A
```

> ⚠️ **The nuance:** "Design = problem solving" is true but incomplete. Design also involves *problem finding* (framing what's actually wrong) and *meaning making* (why should anyone care?). A perfectly solved wrong problem is still a failure.

**See also:** [The Double Diamond](#-node-9--the-design-process), [Wicked problems vs puzzles](#-node-0--what-is-design)

---

## 🧠 Node 1 — Constructivism & Schemata (Why This Document Is Shaped Like This)

You asked about Constructivism and schemata. Both matter twice here: once for *how you learn design*, and once for *how your users experience your design*.

### Constructivism (the learning theory)

**Definition:** Knowledge isn't transferred into your head like a file copy. You *construct* it by connecting new information to what you already know. Key figures: **Jean Piaget** (cognitive constructivism), **Lev Vygotsky** (social constructivism).

Piaget's two core mechanisms:

| Mechanism | What happens | Design-learning example |
|---|---|---|
| **Assimilation** | New info fits into an existing schema | "Oh, a design token is just a variable. I know variables." |
| **Accommodation** | New info breaks the schema, forcing you to rebuild it | "Wait, beautiful design *lowered* conversion? My schema 'pretty = good' is wrong." |

### Schemata (the mental structures)

**Definition:** A **schema** (plural: *schemata*) is an organized mental framework: a cluster of related concepts, expectations, and patterns. The term comes from Piaget and from **Frederic Bartlett's** memory research (1932).

A wiki is basically a schema made visible. Nodes, links, hierarchy. That's why this document is wiki-shaped: the format mirrors the cognitive structure you're trying to build.

### The bridge to UX: users have schemata too

Here is the punchline. In UX, a user's schema is called a **mental model**, and it's one of the most powerful forces in interface design.

```mermaid
flowchart TD
    A["Schema Theory<br/>(Piaget, Bartlett)"] --> B["Mental Models<br/>(how users THINK a system works)"]
    B --> C["Jakob's Law<br/>'Users spend most of their time on OTHER sites'"]
    C --> D["Design implication:<br/>Match conventions unless you have<br/>a very good reason not to"]
    B --> E["Norman's Gulf of Execution<br/>(user can't figure out HOW to act)"]
    B --> F["Norman's Gulf of Evaluation<br/>(user can't tell WHAT happened)"]
    E --> G[Confusion, abandonment]
    F --> G
```

When your interface matches the user's schema, it feels "intuitive." When it violates the schema, the user must *accommodate* (rebuild their mental model), and accommodation costs effort. Users mostly refuse to pay that cost. They just leave.

> 💡 **Rule of thumb:** "Intuitive" is not a property of your design. It's a property of the *match between your design and the user's existing schemata.*

**See also:** [UX Laws](#-node-4--the-laws--heuristics-of-ux), [Why ugly sites convert](#-node-8--aesthetics-vs-conversion-the-paradox)

---

## 🔀 Node 2 — UI vs UX (They Are Not the Same Thing)

**UX (User Experience):** The *entire* journey: how someone discovers, learns, uses, struggles with, and feels about a product. UX includes things you never see on screen: loading speed, support emails, the pricing page, the cancellation flow.

**UI (User Interface
code-architectSubagent

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

code-explorerSubagent

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development

code-reviewSubagent

Code review a pull request

code-simplifierSubagent

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

commitSlash Command

Commit what is already staged — runs the commit subagent in the background, following the ATLAS commit convention.

qa-manual-testerSubagent

Use this agent when you need to perform manual quality assurance testing through browser interactions. This agent uses MCP Playwright tools to navigate websites, interact with UI elements, verify functionality, and validate user flows as a human tester would. Perfect for testing new features, regression testing, validating bug fixes, or exploring application behavior. Examples:\n\n<example>\nContext: The user has just implemented a new login feature and wants to test it.\nuser: "I've added a new login form, can you test if it works correctly?"\nassistant: "I'll use the qa-manual-tester agent to test the login functionality through the browser."\n<commentary>\nSince the user needs manual testing of a new feature, use the Task tool to launch the qa-manual-tester agent to interact with the browser and verify the login flow.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to verify that a bug fix is working properly.\nuser: "I fixed the issue where the submit button wasn't working on mobile view. Can you verify?"\nassistant: "Let me launch the qa-manual-tester agent to verify the submit button works correctly in mobile view."\n<commentary>\nThe user needs manual verification of a bug fix, so use the qa-manual-tester agent to test the specific functionality through browser interaction.\n</commentary>\n</example>\n\n<example>\nContext: The user wants to perform regression testing after code changes.\nuser: "I've refactored the checkout flow. Please test that everything still works."\nassistant: "I'll use the qa-manual-tester agent to perform comprehensive testing of the checkout flow."\n<commentary>\nSince the user needs regression testing after refactoring, use the qa-manual-tester agent to manually test the entire checkout flow.\n</commentary>\n</example>

change-core-selfSlash Command

Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt for it — free to drop KISS/YAGNI/DRY/clean-architecture entirely when the project (and the LLM's own distribution) calls for a different mindset

get-to-knowSlash Command

Initialize project context — understand the project, configure conventions, and set up project rules