agentleFS
samsam007bsamsam007b/claude-code-standards-kit/skills/ux-cognitive-load-check/SKILL.md

ux-cognitive-load-check

Skill2 starsChanged 8 months agoMITView on GitHub

Analyze the cognitive load of a UI component or page. Score based on Miller's Law, Hick's Law, and visual complexity.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If > 7 visible elements → Chunking or Progressive Disclosure

    line 49
  2. Distinctive:

    If > 9 choices → Reduce options or steps

    line 50
  3. Distinctive:

    If visual complexity is high → Simplify the design

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UX Cognitive Load Check Skill

Description

Analyzes the cognitive load of a component or page. Computes a score based on Miller's Law, Hick's Law, and visual complexity. Suggests optimizations if the load is too high.

Usage

/ux-cognitive-load-check [file_path_or_url]

Workflow

  1. Analysis of Visible Elements
    • Counts all interactive elements (buttons, inputs, links)
    • Counts visual sections/groups
    • Identifies the choices to be made (checkboxes, selects, radios)
  2. Cognitive Load Score Calculation
    Cognitive Load Score (0-100) :
    
    Score = 100 - (
      (visible_elements - 7) × 5 +    // Miller's Law penalty
      (choices - 9) × 3 +              // Hick's Law penalty
      (visual_complexity) × 2          // Aesthetic penalty
    )
    
    where:
    - visible_elements = number of distinct elements
    - choices = number of decisions to make
    - visual_complexity = score 0-10 (colors, fonts, spacing)
  3. Classification
    • 0-30: 🔴 CRITICAL - Major redesign required
    • 31-50: 🟠 HIGH - Optimizations needed
    • 51-70: 🟡 MEDIUM - Improvements recommended
    • 71-85: 🟢 GOOD - Acceptable load
    • 86-100: ✅ EXCELLENT - Optimal
  4. Specific Recommendations
    • If > 7 visible elements → Chunking or Progressive Disclosure
    • If > 9 choices → Reduce options or steps
    • If visual complexity is high → Simplify the design

Examples

Example 1: Overloaded search page

/ux-cognitive-load-check app/seeker/explore/page.tsx

Output:

🔴 COGNITIVE LOAD: CRITICAL (Score: 28/100)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
ANALYSIS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Visible Elements: 47 (❌ Exceeds Miller's Law by 40 elements)
├─ Filters: 32 checkboxes
├─ Controls: 8 buttons
├─ Navigation: 7 links
└─ Content: Multiple property cards

Choices Required: 35 (❌ Exceeds Hick's Law by 26 choices)
├─ Filter selections: 32
├─ Sort options: 3

Visual Complexity: 8/10 (⚠️ High)
├─ Colors used: 12 different colors
├─ Font sizes: 8 different sizes
├─ Spacing inconsistencies: 15 detected

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VIOLATIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

1. Miller's Law: 47 elements vs 7±2 recommended
   → Users cannot hold all options in working memory
   → Decision paralysis likely

2. Hick's Law: 35 choices presented simultaneously
   → Decision time: ~8-12 seconds (vs optimal < 3 seconds)
   → High abandonment risk

3. Aesthetic & Minimalist: Visual complexity 8/10
   → Too many visual elements competing for attention

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
RECOMMENDATIONS (Priority Order)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🔴 P0 - Critical (Implement First)
├─ Apply Progressive Disclosure to filters
│  └─ Show only 5-7 essential filters by default
│  └─ Collapse 25+ advanced filters into drawer
│  └─ Estimated impact: Score 28 → 65 (+37)
│
└─ Chunk filters into categories
   └─ Group by: Price, Type, Amenities, Rules, Match
   └─ Estimated impact: Score 65 → 72 (+7)

🟠 P1 - High Priority
├─ Reduce visual complexity
│  └─ Limit to 3-4 brand colors
│  └─ Standardize font sizes (max 5 variations)
│  └─ Estimated impact: Score 72 → 78 (+6)
│
└─ Add "Quick Filters" preset buttons
   └─ Example: "Furnished < 1000€", "2 bed WiFi"
   └─ Reduces choices from 35 to 5-8
   └─ Estimated impact: Score 78 → 85 (+7)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
PROJECTED SCORE AFTER FIXES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Current:  28/100 🔴 CRITICAL
After P0: 72/100 🟢 GOOD
After P1: 85/100 ✅ EXCELLENT

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Example 2: Dashboard with acceptable load

/ux-cognitive-load-check app/seeker/page.tsx

Output:

✅ COGNITIVE LOAD: EXCELLENT (Score: 88/100)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
ANALYSIS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Visible Elements: 6 (✅ Within Miller's Law: 7±2)
├─ KPIs: 4 stat cards
├─ CTA: 1 main button
└─ Navigation: 1 menu

Choices Required: 5 (✅ Within Hick's Law: < 9)

Visual Complexity: 3/10 (✅ Low - Clean design)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
STRENGTHS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✅ Respects Miller's Law: Only 6 elements in glanceable zone
✅ Respects Hick's Law: Limited to 5 clear choices
✅ Visual Hierarchy: Clear F-pattern applied
✅ Progressive Disclosure: Details hidden until needed
✅ Consistent Design: Unified color palette & spacing

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MINOR IMPROVEMENTS (Optional)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🟡 P2 - Nice to Have
└─ Add hover tooltips on KPI cards
   └─ Explain what each metric means
   └─ Estimated impact: Score 88 → 92 (+4)

Output Files

The skill generates:

  1. Terminal output (score + recommendations)
  2. Report file: docs/ux-audits/cognitive-load-[component]-[date].md
  3. Heatmap visual (optional): ASCII art showing attention zones

Configuration

Available flags:

  • --strict: Strict mode (doubled penalties)
  • --export=pdf: Exports the report as PDF
  • --compare=[other_file]: Compares with another component

References

Based on:

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.