Use when adding new error messages to React, or seeing "unknown error code" warnings.
npx skills add erichowens/some_claude_skills --skill "ux-friction-analyzer"
Install specific skill from multi-skill repository
# Description
Comprehensive UX analysis using cognitive psychology, ADHD-friendly design, Gestalt principles, and flow state engineering. Specializes in friction audits, user journey simulation, cognitive load optimization, and Fitts' Law application. Activate on "analyze UX", "friction audit", "user journey", "ADHD-friendly", "optimize flow", "reduce cognitive load", "UX audit", "conversion optimization". NOT for visual design execution (use web-design-expert), A/B testing implementation (use frontend-developer), or accessibility compliance auditing (use accessibility-auditor).
# SKILL.md
name: ux-friction-analyzer
description: Comprehensive UX analysis using cognitive psychology, ADHD-friendly design, Gestalt principles, and flow state engineering. Specializes in friction audits, user journey simulation, cognitive load optimization, and Fitts' Law application. Activate on "analyze UX", "friction audit", "user journey", "ADHD-friendly", "optimize flow", "reduce cognitive load", "UX audit", "conversion optimization". NOT for visual design execution (use web-design-expert), A/B testing implementation (use frontend-developer), or accessibility compliance auditing (use accessibility-auditor).
allowed-tools: Read,Write,Edit,WebFetch
category: Design & Creative
tags:
- ux
- accessibility
- cognitive-load
- adhd-friendly
- user-research
pairs-with:
- skill: web-design-expert
reason: Implement UX recommendations
- skill: adhd-design-expert
reason: Deep neurodivergent design patterns
- skill: frontend-developer
reason: Technical implementation of UX fixes
UX Friction Analyzer
A comprehensive skill for analyzing and optimizing user experience through cognitive psychology, ADHD-friendly design, and flow state engineering.
Activation
Use this skill when:
- Designing new interfaces or user flows
- Auditing existing UX for friction points
- Optimizing for neurodivergent users (ADHD, autism)
- Simulating user journeys before building
- Reducing cognitive load in complex applications
Trigger phrases: "analyze UX", "friction audit", "user journey", "ADHD-friendly", "optimize flow", "reduce cognitive load"
Core Frameworks
1. ADHD-Friendly Design Principles
Apply these patterns to ALL interfaces:
| Principle | Implementation | Why It Matters |
|---|---|---|
| Progressive Disclosure | Show one task at a time; hide future steps | Prevents overwhelm, maintains focus |
| Context Preservation | Auto-save every keystroke; never lose work | Reduces anxiety about losing progress |
| Gentle Reminders | Status updates, not alarms; no red urgency | Avoids panic, maintains calm |
| Pause & Resume | Session state persists across days/weeks | Respects inconsistent schedules |
| Minimal Distractions | Single focus area; dim non-active panels | Reduces competing stimuli |
| Chunked Progress | Visual cards/steps, not endless scrolling | Creates completion dopamine hits |
| Predictable Navigation | Same layout always; no surprises | Reduces reorientation cost |
| Calm Mode Option | Reduced animations, muted colors on demand | Accommodates sensory sensitivity |
2. Gestalt Psychology
Apply these perception principles:
PROXIMITY
βββββββββ
Elements close together = perceived as related
White space creates natural boundaries
βββββββββββ βββββββββββ βββββββββββ βββββββββββ
β Related β β Related β β Other β β Other β
β Item A β β Item B β β Group A β β Group B β
βββββββββββ βββββββββββ βββββββββββ βββββββββββ
β CLOSE = GROUPED β SEPARATE = DISTINCT
SIMILARITY
ββββββββββ
Same color/shape/size = perceived as related function
ββββββββ ββββββββ ββββββββ ββββββββ ββββββββ
β BLUE β β BLUE β β BLUE β β CORALβ β CORALβ
β Save β β Copy β β Edit β β Del β β Clearβ
ββββββββ ββββββββ ββββββββ ββββββββ ββββββββ
β SAME = Related actions β DIFFERENT = Destructive
CONTINUITY
ββββββββββ
Eye follows lines/paths naturally
Step 1 βββ Step 2 βββ Step 3 βββ Complete
ββββββββββββββββββββββββββββββββββ
CLOSURE
βββββββ
Brain completes incomplete shapes
Use for progress indicators, loading states
[ ββββββββββββββββ ] 50% - brain "sees" the end
3. Cognitive Load Theory
Three types of mental load to manage:
| Type | Definition | Strategy |
|---|---|---|
| Intrinsic | Task complexity itself | Can't eliminate; acknowledge it |
| Extraneous | Poor design adding effort | ELIMINATE THIS - your job |
| Germane | Learning/understanding | Minimize for repeat users |
Working Memory Limits:
- 7Β±2 items maximum (Miller's Law)
- 4 chunks optimal for complex tasks
- Micro-breaks every 25 minutes
Reduce Extraneous Load By:
- Removing unnecessary choices
- Using recognition over recall
- Providing smart defaults
- Eliminating decorative elements that don't inform
4. Fitts' Law
Time to acquire target = f(Distance / Size)
IMPLICATIONS FOR BUTTONS:
βββββββββββββββββββββββββ
βββββββββββββββββββββ vs ββββ
β GENERATE β βGoβ
β β ββββ
βββββββββββββββββββββ
β β
44px+ touch target Hard to hit
Easy to acquire Frustrating
MINIMUM SIZES:
- iOS: 44x44 CSS pixels
- Android: 48x48 CSS pixels
- Desktop: 32x32 minimum, 44x44 preferred
EDGE TARGETS ARE INFINITE:
βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β β LOGO MENU β β
β β
β Screen edges = can't overshoot β
β Place critical actions at corners/edges β
β β
β β HELP EXPORT β β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ICON + LABEL > ICON ALONE:
- Larger target area
- Reduced ambiguity
- Faster acquisition
5. Flow State Engineering
Key Metrics:
- 15-25 minutes to enter flow state
- 23 minutes to recover from interruption
- 40% productivity loss with frequent interruptions
- Only 41% of work time spent in flow (McKinsey)
Flow Conditions:
1. Clear goals for the current task
2. Immediate feedback on actions
3. Balance between challenge and skill
4. No anxiety about failure
Preserve Flow By:
- Background processing (don't block UI)
- Push notifications when ready (bring user back faster)
- Quick re-orientation panels after breaks
- Auto-save eliminating "save anxiety"
- Undo everything (confidence to experiment)
Analysis Methodology
Step 1: Create Decision Tree
Map every user path with probabilities:
βββββββββββββββ
β USER LANDS β
ββββββββ¬βββββββ
β
βββββββββββββββββΌββββββββββββββββ
βΌ βΌ βΌ
ββββββββββββ ββββββββββββ ββββββββββββ
β Action A β β Action B β β Action C β
β (40%) β β (45%) β β (15%) β
ββββββ¬ββββββ ββββββ¬ββββββ ββββββ¬ββββββ
β β β
βΌ βΌ βΌ
[Next] [Next] [Next]
For each edge, record:
- Probability (%)
- Friction score (1-10)
- Time to complete (seconds/minutes)
- Cognitive load (low/medium/high)
Step 2: Simulate User Journeys
Create detailed simulations for each persona:
Template:
TIME ACTION COGNITIVE STATE FRICTION
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
0:00 [User action] [Mental state] Low/Med/High
ββ [System response or UI shown]
0:15 [Next action] [How they feel] Low/Med/High
ββ [What happens]
ββ PROBLEM: [Friction point if any]
...continue...
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
TOTAL TIME: X minutes
FRICTION POINTS: N (list them)
ABANDONMENT RISKS: N (critical moments)
DELIGHT MOMENTS: N (positive surprises)
Personas to simulate:
1. Expert User - Knows the system, moving fast
2. New User - First time, needs guidance
3. Distracted User - Context switching, interruptions
4. Explorer - No goal, seeing what's possible
5. Completer - Trying to finish, hitting obstacles
Step 3: Friction Analysis Matrix
Quantify and prioritize:
| Friction Point | Users Affected | Severity (1-10) | Fix Difficulty | Priority Score |
|---|---|---|---|---|
| [Issue 1] | X% | N | Easy/Med/Hard | HIGH/MED/LOW |
| [Issue 2] | X% | N | Easy/Med/Hard | HIGH/MED/LOW |
Priority Formula:
Priority = (Users Affected Γ Severity) / Fix Difficulty
Step 4: Impedance Mapping
Compare current vs ideal:
TASK CURRENT IMPEDANCE IDEAL IMPEDANCE
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
[Task 1] Low (X sec) β Optimal
[Task 2] Medium (X sec) Could be Y sec
[Task 3] HIGH (X min) Should be Y sec
Step 5: Time-Loss Analysis
Calculate context switch costs:
Action Frequency Time Lost Each Total Impact
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
[Interruption type 1] X/session Y min Z min
[Interruption type 2] X/session Y min Z min
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
TOTAL CONTEXT SWITCH LOSS Z min/session
Optimization Patterns
Immediate Fixes (Low Effort, High Impact)
-
Giant CTA on Landing
html <button class="cta" style="min-height: 60px; min-width: 200px;"> Primary Action <span class="subtext">Supporting text</span> </button> -
Visible Edit Affordances
- Show pencil/edit icons by default, not just on hover
-
Add tooltips: "Click to edit"
-
Auto-Fill Prompts
- After user completes 1 item manually, offer to auto-complete rest
-
"Want me to fill in the remaining X items?"
-
Floating Action Buttons
- Critical actions always visible (not buried in menus)
-
Bottom-right for mobile thumb zone
-
Progress Indicators
- Show "Step X of Y" always
- Visual progress bar at top
Medium-Term Improvements
-
Re-Orientation Panels
βββββββββββββββββββββββββββββββββββββββββββββββ β Welcome back! Here's where you left off: β β β β β Step 1: Complete β β β Step 2: In progress (60%) β β β Step 3: Not started β β β β [Continue where I left off] β βββββββββββββββββββββββββββββββββββββββββββββββ -
Keyboard Shortcuts
- Number keys for mode switching (1, 2, 3...)
- Cmd+Enter for primary action
-
Escape for cancel/close
-
Background Processing
- Never block UI for long operations
- Show progress, allow user to continue
-
Push notification when complete
-
Smart Defaults
- Pre-fill based on user history
- Remember last-used settings
- Suggest most common option first
Long-Term Vision
- Predictive UI
- Anticipate next action based on patterns
- Pre-load likely next screens
-
Suggest before user asks
-
Personalized Complexity
- Simple mode for new users
- Power user mode unlocks over time
-
User controls their complexity level
-
Accessibility Suite
- High contrast mode
- Reduced motion option
- Screen reader optimization
- Keyboard-only navigation
Checklist for New Features
Before shipping any feature, verify:
Cognitive Load
- [ ] Can user complete with β€4 things in working memory?
- [ ] Are there unnecessary choices that could be defaults?
- [ ] Is recognition used instead of recall?
ADHD-Friendly
- [ ] Can user pause and resume without losing context?
- [ ] Are there gentle progress indicators (not anxiety-inducing)?
- [ ] Is the interface calm (not visually noisy)?
Fitts' Law
- [ ] Are primary buttons β₯44px tall?
- [ ] Are destructive actions away from common paths?
- [ ] Do buttons have labels, not just icons?
Flow Preservation
- [ ] Does any action block the UI for >2 seconds?
- [ ] Can long operations run in background?
- [ ] Is there a clear "done" state?
Error Recovery
- [ ] Can every action be undone?
- [ ] Are error messages actionable (not just "Error")?
- [ ] Is auto-save enabled?
Example Analysis Output
When running this skill, produce a document with:
- Executive Summary - Key findings in 3 bullets
- Decision Tree - All user paths with probabilities
- User Journey Simulations - 3-5 personas, full timeline
- Friction Matrix - Prioritized issues table
- Optimization Recommendations - Immediate/Medium/Long-term
- Implementation Checklist - Specific changes to make
Integration Points
- web-design-expert: Implement UX recommendations visually
- adhd-design-expert: Deep neurodivergent design patterns
- frontend-developer: Technical implementation of fixes
- diagramming-expert: Create user flow diagrams
Sources
- NN/g: Minimize Cognitive Load
- NN/g: Fitts's Law
- Laws of UX
- IxDF: Gestalt Principles
- Stack Overflow: Developer Flow State
- Medium: ADHD UX Design
Core Philosophy: Every click, every second of confusion, every moment of "where am I?" is friction stealing from your users. Design for the distracted, optimize for the overwhelmed, and everyone benefits.
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.