UX Design
Design user experiences including wireframes, flows, and interaction patterns. Use this skill when UX design work is requested, including onboarding flows and interface layouts.
Best use case
UX Design is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Design user experiences including wireframes, flows, and interaction patterns. Use this skill when UX design work is requested, including onboarding flows and interface layouts.
Teams using UX Design should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ux-design/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How UX Design Compares
| Feature / Agent | UX Design | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Design user experiences including wireframes, flows, and interaction patterns. Use this skill when UX design work is requested, including onboarding flows and interface layouts.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Skill: UX Design ## Metadata | Field | Value | |-------|-------| | **Skill ID** | SKL-0023 | | **Version** | 1.0 | | **Owner** | designer | | **Inputs** | Task description, STATE.md, DECISIONS.md, PRD, existing designs, target platform | | **Outputs** | Design doc at docs/ux/, DECISIONS.md updated, STATE.md updated | | **Triggers** | `UX_DESIGN_REQUESTED` | --- ## Purpose Design user experiences that are intuitive, accessible, and implementable. Every screen must be designed before it is built. Work upstream of the builder agent — their input is this skill's output. --- ## Procedure 1. **Define the user and their goal:** - Who is the user? (persona or role) - What are they trying to accomplish? - Where are they coming from? (entry point) - What does success look like? 2. **Map the full user flow** before designing screens: - Happy path from entry to completion - Decision points where the flow branches - Error paths — what happens when things go wrong - Edge cases — empty states, first-time use, returning users 3. **Design each screen** in the flow: - **Layout:** what elements appear and where - **Content:** exact labels, headings, button text (not lorem ipsum) - **Interactions:** what happens on tap, click, swipe, submit - **States:** loading, error, empty, and populated — all four, every screen 4. **Apply UX principles:** - **Clarity:** one primary action per screen, plain language labels, error messages tell user what to do next - **Reduce friction:** minimize taps, default to common choice, never re-enter provided info - **Platform conventions:** iOS (nav bar top, tab bar bottom), Android (bottom nav, back button), Web (persistent nav, breadcrumbs, hover states) - **Beginner-friendly:** assume first-time user, empty states explain what to do, onboarding shows value before asking 5. **Design onboarding** (for new apps/major features): - Show value before asking for anything - Ask for minimum permissions, only when needed - Progress indicators — user knows how long it takes - Skip option for experienced users - First success moment within 60 seconds - Template: define first launch goal, value moment, minimum required before value, deferred asks, steps, skip path, re-entry 6. **Usability gut-check:** - Can a new user find the primary action in under 5 seconds? - Is there anything that could be removed? - Does every element earn its place? - What would confuse a first-time user? 7. **Write design document** to `docs/ux/[feature-name]-flow.md`. 8. **Log UX decisions** to DECISIONS.md. 9. **Update STATE.md.** --- ## Constraints - Never writes code — design only - Never skips user flow map and jumps to screen design - Never skips onboarding design for a new app or major feature - Never designs a screen without defining its empty and error states - Always writes designs implementable without further clarification - Always uses plain language — no design jargon --- ## Primary Agent designer --- ## Definition of Done - [ ] User and goal defined before designing - [ ] Full user flow mapped including alternative paths - [ ] Every screen designed with layout, interactions, and all four states - [ ] Onboarding flow designed with value moment identified (for new apps) - [ ] UX principles applied and gut-check completed - [ ] Design document written to docs/ux/[feature-name]-flow.md - [ ] UX decisions logged to DECISIONS.md - [ ] STATE.md updated ## Knowledge Enhancement (MCP mode) If Cortex MCP is available: 1. Call `search_knowledge` with query derived from task (e.g., "onboarding patterns mobile", "navigation patterns SaaS", "form design best practices"), category="ux-design" 2. If relevant results found, call `get_fragment` on the top result 3. Apply as supplementary context (does not override this skill's procedure) ## Output Contract | Field | Value | |-------|-------| | **Artifacts** | `docs/ux/[feature-name]-flow.md` | | **State Update** | `.claude/project/STATE.md` — mark task complete, log files modified | | **Decision Log** | `.claude/project/knowledge/DECISIONS.md` — UX decisions | | **Handoff Event** | `TASK_COMPLETED` (UX design complete) |
Related Skills
Supply Chain Audit
Audit the dependency supply chain for security risks beyond what `npm audit` or `pip audit` catches. Analyzes dependency health, maintainer trust signals, typosquatting risk, and transitive dependency exposure.
SEO Audit
Audit web pages for search engine optimization: meta tags, heading hierarchy, structured data, image optimization, mobile-friendliness, and content quality. Complements SKL-0013 (Growth & Distribution) by validating what was built.
Pitch Deck
Create a structured pitch deck outline for investors, stakeholders, or partners. Covers problem, solution, market, traction, team, and ask. Natural output after PRD + Problem Stress Test validation.
Launch Checklist
Pre-launch validation covering everything deployment (SKL-0021) doesn't: analytics, error tracking, social meta, legal pages, email setup, DNS, SSL, and go-live readiness. Produces a launch readiness report with pass/fail checklist. Use this skill before going live on any project.
Insecure Defaults Detection
Detect insecure default configurations, hardcoded credentials, fail-open security patterns, and dangerous default values in application code and configuration files. Complements SKL-0015 (Security Audit) by focusing on configuration-level vulnerabilities that dependency scanners miss.
Differential Security Review
Security-focused review of code changes using git diff analysis. Identifies security implications of recent modifications — new attack surfaces, removed protections, changed auth logic, and risky refactors. Complements SKL-0016 (Code Review) with a security lens on diffs.
Copywriting
Write conversion-focused copy using proven frameworks (AIDA, PAS, BAB). Produces headlines, CTAs, landing page copy, email sequences, and micro-copy. Ensures copy matches brand voice and target audience.
Competitor Analysis
Structured competitor research: features, pricing, positioning, gaps, and differentiation strategy. Feeds into PRD Writing (SKL-0004) and Problem Stress Test (SKL-0027) with better market context.
User Acceptance Testing
Structured QA testing with four modes: diff-aware (auto-scoped to branch changes), full (systematic exploration), quick (30-second smoke test), and regression (compare against baseline). Produces health score, structured reports, and actionable bug lists. Use this skill when UAT is requested or a feature is ready for acceptance testing.
Token Audit
Audit the current project for token waste patterns. Produces a Token Health Report with scored findings and actionable fixes. Use this skill when token usage feels high, sessions are hitting limits, or before optimizing costs.
Test Writing
Write automated tests for existing or new functionality. Use this skill when tests are requested, including unit tests, integration tests, and end-to-end tests.
Skill Creator
Turn a repetitive workflow into a reusable custom skill. Interviews the user, then produces a complete SKILL.md with frontmatter, procedure, constraints, definition of done, and output contract in custom-skills/. Use this skill when you find yourself repeating the same process and want to automate it.