ux-researcher-designer
Use when the user needs user research methodologies, persona development, journey mapping, usability testing plans, or information architecture analysis. Triggers: user says "user research", "persona", "journey map", "usability test", "card sort", "heuristic evaluation", "information architecture", "user interview", understanding user behavior.
What this skill does
# UX Researcher & Designer
## Overview
Apply systematic UX research and design methods to understand users, validate assumptions, and create evidence-based designs. This skill covers the full research-to-design pipeline: discovery research, persona creation, journey mapping, information architecture, usability testing, and heuristic evaluation.
## Phase 1: Discovery Research
1. Define research objectives and questions
2. Select appropriate research methods
3. Recruit participants (5-8 per segment for qualitative)
4. Conduct research sessions
5. Synthesize findings using affinity mapping
**STOP — Present research plan with objectives and methods for user approval.**
### Research Method Selection Decision Table
#### Generative (Discovery) Methods
| Method | When to Use | Participants | Duration | Cost |
|---|---|---|---|---|
| User Interviews | Understanding motivations, behaviors, pain points | 5-8 per segment | 45-60 min each | Medium |
| Contextual Inquiry | Observing users in their natural environment | 4-6 | 1-2 hours each | High |
| Diary Studies | Longitudinal behavior patterns | 10-15 | 1-4 weeks | Medium |
| Surveys | Quantitative validation of qualitative findings | 100+ | 5-10 min | Low |
| Focus Groups | Exploring attitudes and preferences | 6-10 per group | 60-90 min | Medium |
#### Evaluative Methods
| Method | When to Use | Participants | Duration | Cost |
|---|---|---|---|---|
| Usability Testing | Validating designs against tasks | 5-8 | 30-60 min each | Medium |
| A/B Testing | Comparing two design variants | 1000+ per variant | 1-4 weeks | Low |
| Card Sorting | Organizing information architecture | 15-30 | 20-30 min | Low |
| Tree Testing | Validating navigation structure | 50+ | 10-15 min | Low |
| First Click Testing | Evaluating initial user instincts | 30+ | 5-10 min | Low |
| Heuristic Evaluation | Expert review without users | 3-5 evaluators | 1-2 hours | Low |
#### Method Selection Decision Table
| Situation | Recommended Method | Why |
|---|---|---|
| No idea who users are | Interviews + contextual inquiry | Deep understanding needed |
| Have assumptions to validate | Surveys + usability testing | Quantitative confirmation |
| Redesigning navigation | Card sorting + tree testing | Structure-focused |
| Evaluating existing product | Heuristic evaluation + usability test | Find problems fast |
| Comparing two designs | A/B testing | Statistical comparison |
| Limited budget/time | Heuristic evaluation | No participants needed |
| Long-term behavior understanding | Diary study | Captures patterns over time |
### Interview Guide Template
```
1. Introduction (5 min)
- Thank participant, explain purpose
- Get consent for recording
- "There are no wrong answers"
2. Warm-up (5 min)
- Background questions about role/context
- Current tools and workflows
3. Core Questions (30 min)
- Open-ended questions about behaviors
- Follow-up probes: "Tell me more about..."
- Critical incident: "Describe a time when..."
- Avoid leading questions
4. Wrap-up (5 min)
- "Is there anything I didn't ask that you think is important?"
- Thank and explain next steps
```
## Phase 2: Analysis and Modeling
1. Create user personas from research data
2. Map user journey for key scenarios
3. Define information architecture
4. Identify pain points and opportunities
5. Prioritize using impact/effort matrix
**STOP — Present personas and journey map for review before design validation.**
### Persona Template
```markdown
# [Persona Name]
## Demographics
- Age: [range]
- Occupation: [role]
- Technical proficiency: [low/medium/high]
- Usage frequency: [daily/weekly/monthly]
## Goals
1. Primary goal: [what they are trying to achieve]
2. Secondary goal: [supporting objective]
3. Tertiary goal: [nice-to-have]
## Pain Points
1. [Frustration with current process]
2. [Unmet need]
3. [Workaround they have created]
## Behaviors
- [How they currently solve the problem]
- [Tools and methods they use]
- [Decision-making patterns]
## Quotes (from research)
- "[Verbatim quote that captures their perspective]"
- "[Another representative quote]"
## Scenario
[A paragraph describing a typical day/task where they would use the product]
```
### Persona Quality Decision Table
| Check | Pass | Fail |
|---|---|---|
| Based on real research data | Quotes and behaviors from interviews | Invented or assumed behaviors |
| Actionable for design | Specific goals and pain points | Vague "wants to be productive" |
| Distinct from other personas | Different goals, behaviors, constraints | Overlapping with another persona |
| Number of personas | 2-4 primary | More than 5 (too many to design for) |
### Journey Map Structure
```
Stages: Awareness -> Consideration -> Onboarding -> Usage -> Advocacy
| | | | |
Actions: [What they do at each stage]
| | | | |
Thoughts: [What they are thinking]
| | | | |
Emotions: [Frustration/neutral/delight mapped to each stage]
| | | | |
Pain Points: [Friction and frustration points]
| | | | |
Opportunities: [Design opportunities to improve]
| | | | |
Touchpoints: [Channels and interfaces involved]
```
### Journey Map Elements
- **Moments of Truth**: Critical points where users form lasting impressions
- **Service Blueprints**: Front-stage actions mapped to back-stage processes
- **Emotion Curve**: Visual line showing emotional highs and lows
- **Gap Analysis**: Difference between current and desired experience
### Heuristic Evaluation (Nielsen's 10)
| # | Heuristic | What to Look For |
|---|---|---|
| 1 | Visibility of system status | Loading indicators, progress bars, save confirmations |
| 2 | Match with real world | Natural language, familiar metaphors, logical order |
| 3 | User control and freedom | Undo, cancel, back, escape hatches |
| 4 | Consistency and standards | Same action = same result, platform conventions |
| 5 | Error prevention | Confirmation dialogs, constraints, smart defaults |
| 6 | Recognition over recall | Visible options, contextual help, recent history |
| 7 | Flexibility and efficiency | Shortcuts, customization, bulk actions |
| 8 | Aesthetic and minimalist design | No unnecessary information, clear hierarchy |
| 9 | Help users with errors | Plain language errors, specific cause, suggest fix |
| 10 | Help and documentation | Searchable, task-oriented, concise |
### Severity Rating Scale
| Rating | Description | Action |
|---|---|---|
| 0 | Not a usability problem | No action |
| 1 | Cosmetic only | Fix if time allows |
| 2 | Minor problem | Low priority fix |
| 3 | Major problem | High priority, fix before launch |
| 4 | Usability catastrophe | Must fix immediately |
## Phase 3: Design Validation
1. Create testable prototypes (low or high fidelity)
2. Plan usability testing sessions
3. Conduct tests with 5+ participants
4. Analyze results and iterate
5. Document findings and recommendations
**STOP — Present usability test results and recommendations for review.**
### Prototype Fidelity Decision Table
| Situation | Fidelity | Tool | Why |
|---|---|---|---|
| Early concept validation | Low (paper/wireframe) | Balsamiq, paper | Fast iteration, low commitment |
| Navigation testing | Medium (clickable) | Figma prototype | Test flow without visual polish |
| Visual design validation | High (pixel-perfect) | Figma, coded prototype | Test actual look and feel |
| Interaction validation | High (coded) | HTML/CSS/JS prototype | Test real interactions |
### A/B Testing Methodology
| Step | Details |
|---|---|
| Hypothesis | "Changing [X] will [improve/decrease] [metric] because [reason]" |
| Sample size | Power analyRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.