Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Ui Ux Designer

ASecurity

Design user interfaces and experiences from research and flows to wireframes, mockups, and usability testing.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgotesting

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill ui-ux-designer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ui Ux Designer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ui Ux Designer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-ui-ux-designer/badge)](https://www.skillsdirectory.com/skills/aicodedecode-ui-ux-designer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: ui-ux-designer
description: Design user interfaces and experiences from research and flows to wireframes, mockups, and usability testing.
category: creative-design
---

## Overview

UI/UX design is problem-solving made visible: understanding what users need,
structuring it into
flows, and crafting interfaces that feel obvious. This skill covers the full arc
— user research,
information architecture, wireframing, visual design, prototyping, and testing —
with an emphasis on
decisions you can defend, not just screens that look nice.

## When to use

- Designing a new app, website, or feature from scratch

- Redesigning an existing product with usability problems

- Creating user flows, wireframes, or high-fidelity mockups

- Planning and running usability tests

- Reviewing designs for UX quality before handoff

## Core concepts

- - - **Jobs to be done.** Users don't want features; they want outcomes. Frame
  every screen around
  the job: "as a [user], I want to [goal] so that [outcome]." If a screen
doesn't serve a job, cut
  it.
- - - **Hierarchy and flow.** Every screen needs one primary action and a clear
  visual hierarchy
  guiding the eye to it. Map the happy path first, then edge cases — not the
reverse.
- - - **Consistency builds trust.** Same patterns for same actions across the
  product. Users shouldn't
  have to relearn your interface on every screen; familiarity is a feature.
- - - **Progressive disclosure.** Show what's needed now; hide the rest behind
  deliberate reveals.
  Complexity should be available, not unavoidable.
- - - **Design for the edge cases.** Empty states, errors, loading, offline,
  long names, right-to-left
  text. The difference between a demo and a product lives here.
- - - **Test with 5 users.** Five usability tests uncover ~85% of issues. Test
  early with rough
  prototypes — fixing a wireframe costs nothing; fixing shipped code costs
sprints.

## Practical workflow

1. 1. 1. **Define the problem.** Who are the users, what job are they hiring
   this product for, what
   does success look like (metrics)? Write a one-paragraph problem statement
before opening any
   design tool.
2. 2. 2. **Research lightly but really.** 3-5 user conversations or
   support-ticket reviews beat
   assumptions. Capture: goals, current workarounds, pain points, mental models.
3. 3. 3. **Map the flow.** User flows for the key journeys: boxes for screens,
   diamonds for decisions.
   Identify the happy path, then branches. Cut steps ruthlessly — every screen
is friction.
4. 4. 4. **Wireframe fast.** Low-fidelity, grayscale, fast. Explore 2-3
   directions for critical
   screens. Get feedback on structure before investing in visuals.
5. 5. 5. **Design high-fidelity.** Apply visual hierarchy, the design system (or
   create the
   foundations), real content (never lorem ipsum in final mocks — content is
design), and responsive
   behavior.
6. 6. 6. **Prototype the interactions.** Clickable prototype covering the key
   flows. Prototype only
   what needs testing — full-app prototypes waste time.
7. 7. 7. **Test and iterate.** 5 moderated tests: give tasks, observe silently,
   note where users
   hesitate. Fix the top 3 issues, retest. Repeat until the flow feels boring —
boring means usable.
8. 8. 8. **Document for handoff.** Annotated specs: behaviors, states, edge
   cases, responsive rules.
   (See design-handoff-specialist for the full handoff practice.)

## Common pitfalls

- - - **Designing for yourself.** Your mental model isn't the user's. Every
  assumption should be
  tested or at least acknowledged as one.
- - - **Dribbble-itis.** Optimizing for visual impressiveness over usability.
  Beautiful screens that
  confuse users are failed designs.
- - - **Skipping the flow.** Designing screens without mapping the journey
  produces disconnected
  experiences and missed states.
- - - **Lorem ipsum forever.** Designing around fake content, then cramming real
  content in later.
  Real headlines, real names, real edge-case strings from the start.
- - - **Ignoring accessibility.** Low contrast, tiny tap targets, keyboard
  traps. Accessibility isn't
  a phase — it's part of every design decision (see
accessibility-design-checker).
- - - **Falling in love with the first idea.** The first solution is rarely the
  best. Explore broadly
  at low fidelity before committing.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →