← Browse

@majiayu000/ux-psychology

B

Apply UX psychology principles to frontend design. Use when designing UI components, improving user experience, increasing conversion, or making design decisions. Covers 43 psychological concepts including cognitive biases, behavioral patterns, visual design principles, and engagement techniques. Triggers on requests like "design a pricing page", "improve signup flow", "increase engagement", or "apply psychology to UI".

skillclaude

Install

agr install @majiayu000/ux-psychology --target claude

Writes 2 files into .claude/skills/, pinned to git-d9a0ae41.

  • .claude/skills/ux-psychology/SKILL.md
  • .claude/skills/ux-psychology/metadata.json

Document


name: ux-psychology description: Apply UX psychology principles to frontend design. Use when designing UI components, improving user experience, increasing conversion, or making design decisions. Covers 43 psychological concepts including cognitive biases, behavioral patterns, visual design principles, and engagement techniques. Triggers on requests like "design a pricing page", "improve signup flow", "increase engagement", or "apply psychology to UI".

UX Psychology for Frontend Design

Apply psychological principles to create more effective, engaging user interfaces.

Workflow

1. Identify Design Goal

Determine the primary objective:

  • Conversion: Pricing, signup, checkout
  • Engagement: Retention, time-on-site, repeat visits
  • Usability: Task completion, error reduction
  • Trust: Credibility, security perception

2. Select Relevant Concepts

Based on goal, consult the appropriate reference file:

GoalReference FileKey Concepts
Conversionreferences/cognitive-biases.mdAnchoring, Loss Aversion, Framing
Engagementreferences/engagement.mdGamification, Variable Reward, Social Proof
Usabilityreferences/behavioral-patterns.mdCognitive Load, Progressive Disclosure, Default Effect
Visual Appealreferences/visual-design.mdAesthetic-Usability, Visual Hierarchy

3. Apply Concepts to Design

For each selected concept:

  1. Read the detailed pattern from reference file
  2. Identify specific UI elements to apply it to
  3. Implement with code examples provided

Quick Reference: 43 Concepts

Cognitive Biases (→ references/cognitive-biases.md)

Anchoring Effect, Confirmation Bias, Expectation Bias, Familiarity Bias, Framing Effect, Halo Effect, Loss Aversion, Sunk Cost Effect, Survey Bias

Behavioral Patterns (→ references/behavioral-patterns.md)

Cognitive Load, Decision Fatigue, Default Effect, Foot-in-the-Door, Goal Gradient Effect, Intentional Friction, Nudge Effect, Progressive Disclosure, Reactance, Reactive Onboarding, Selective Attention, Temptation Bundling, Zeigarnik Effect

Visual Design (→ references/visual-design.md)

Aesthetic-Usability Effect, Banner Blindness, Visual Hierarchy, Visual Anchor, Skeuomorphism, Serial Position Effect, Priming Effect

Engagement (→ references/engagement.md)

Curiosity Gap, Decoy Effect, Doherty Threshold, Empathy Gap, Endowment Effect, Gamification, Hawthorne Effect, Labor Illusion, Peak-End Rule, Pygmalion Effect, Scarcity, Social Proof, User Delight, Variable Reward

Common Design Patterns

Pricing Page

Applied concepts:
- Anchoring: Show highest-priced plan first
- Decoy Effect: Make middle plan look like best value
- Social Proof: "Most Popular" badge
- Visual Anchor: Highlight recommended plan visually

Signup Flow

Applied concepts:
- Foot-in-the-Door: Start with email only, ask details later
- Cognitive Load: One task per screen
- Goal Gradient: Show progress bar
- Default Effect: Pre-select recommended options

E-commerce Product Page

Applied concepts:
- Scarcity: "Only 3 left in stock"
- Social Proof: Reviews and ratings
- Loss Aversion: "Don't miss out..."
- Aesthetic-Usability: High-quality product images

Ethical Guidelines

Dark Patterns to Avoid

  • False scarcity claims
  • Hidden fees
  • Difficult cancellation flows
  • Manipulative loss aversion messaging
  • Forced opt-ins

Ethical UX Design

  • Prioritize user benefit
  • Provide transparent information
  • Respect user choice
  • Build trust over tricks

Source

Based on: https://www.shokasonjuku.com/ux-psychology

Repository README

Describes majiayu000/claude-skill-registry-data as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.

Claude Skill Registry (Data)

This repo contains the archived skill contents (the heavy, browsable skill files).

Canonical layout

  • Category folders at repo root (e.g. development/, documents/, data/, ...)
  • Each skill lives under a category: <category>/<skill>/SKILL.md + <category>/<skill>/metadata.json
  • Case conflicts are resolved with {name}-{owner}-{repo} suffixes (fallback: -{short-hash}).

Archive status

  • Live badges above are sourced from claude-skill-registry-core stats.json.
  • Counts in this README are intentionally dynamic, not hardcoded.
  • If the badges look stale, refresh the core build/index pipeline rather than editing numbers here.

Where the index + site live

Trustgrade B

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • warnLicenseno SPDX license detected

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-d9a0ae4157352026-07-31