decision-toolkit

Original source / Raw SKILL.md

---
name: decision-toolkit
description: Generate structured decision-making tools — step-by-step guides, bias checkers, scenario explorers, and interactive dashboards. Use when facing significant choices requiring systematic analysis. Supports multiple cognitive styles and output formats.
---

# Decision Toolkit

## Overview

Create structured decision support materials that help humans think through significant choices systematically. This skill produces interactive tools, not just analysis — empowering the decision-maker rather than deciding for them.

## Philosophy

### Principles

1. **Guide, don't decide** — Tools illuminate the decision space; humans choose
2. **One thing at a time** — Reduce cognitive load through progressive disclosure
3. **Multiple lenses** — Same decision viewed through different frameworks reveals blind spots
4. **Biases visible** — Make cognitive biases explicit and checkable
5. **Actionable output** — End with concrete next steps, not abstract conclusions

### Accessibility First

- Support screen readers (semantic HTML, ARIA labels)
- Keyboard navigable (tab order, focus states)
- High contrast by default (WCAG AA minimum)
- Reduced motion option
- Works without JavaScript (graceful degradation)
- Mobile-friendly touch targets (44px minimum)

### Cognitive Inclusivity

Different people process decisions differently:

| Style | Accommodation |
|-------|---------------|
| **Analytical** | Numbers, matrices, weighted scores |
| **Intuitive** | Gut-check prompts, "how does this feel?" |
| **Visual** | Diagrams, progress bars, color coding |
| **Verbal** | Written summaries, question prompts |
| **Sequential** | Step-by-step wizard flow |
| **Global** | Dashboard overview option |

## When to Use

Invoke this skill when user faces:
- Collaboration/partnership decisions
- Career or job changes
- Investment of significant time/money
- Project prioritization
- Technology/tool selection
- Any choice with multiple factors and uncertainty

**Not for**: Trivial decisions, emergency responses, or when user just needs information.

## Decision Types

### Type 1: Opportunity Evaluation
*Should I pursue this opportunity?*
- Partnership, job offer, investment, project

### Type 2: Resource Allocation
*Where should I invest my time/money/attention?*
- Prioritization, budgeting, focus areas

### Type 3: Risk Assessment
*What could go wrong and is it worth it?*
- New ventures, changes, experiments

### Type 4: Trade-off Navigation
*Which option among alternatives?*
- Tool selection, hire decisions, strategic choices

## The Decision Journey

Nine steps, each focused on one dimension:

```
┌─────────────────────────────────────────────────────────────┐
│  1. CONTEXT         What is the decision?                   │
│  2. FIRST PRINCIPLES Does this solve a real problem?        │
│  3. TIMING          Is now the right moment?                │
│  4. STAKEHOLDERS    Who else is involved? Are they stable?  │
│  5. BIASES          What might cloud my judgment?           │
│  6. OPPORTUNITY COST What am I giving up?                   │
│  7. SCENARIOS       What could happen?                      │
│  8. QUESTIONS       What do I still need to learn?          │
│  9. SYNTHESIS       Summary + decision                      │
└─────────────────────────────────────────────────────────────┘
```

## Output Formats

### 1. Interactive HTML Guide (Primary)
Step-by-step wizard with:
- Progress indicator
- One question per screen
- State persistence across steps
- Final summary aggregating all inputs
- Keyboard navigation
- Print-friendly CSS

### 2. Markdown Framework
For offline/text-based use:
- Structured prompts
- Checkbox-style bias audit
- Fill-in-the-blank templates

### 3. Voice Summary
For audio consumption:
- 5-7 paragraph executive summary
- Orpheus TTS markup for emotional texture
- Key decision + rationale

### 4. PDF Report
For documentation/sharing:
- Professional formatting
- All frameworks applied
- Appendix with raw analysis

## Frameworks Reference

### First Principles Test
```
1. What problem does this solve?
2. Can I solve it myself?
3. Is this the best solution?
4. What assumptions am I making?
5. If starting fresh today, would I choose this?
```

### Bias Checklist
```
□ FOMO — Am I afraid of missing out?
□ Sunk Cost — Am I factoring past investment?
□ Authority — Am I deferring to credentials?
□ Social Proof — Am I following the crowd?
□ Commitment — Do I feel locked in by past statements?
□ Optimism — Am I assuming problems will resolve?
□ Recency — Am I overweighting recent events?
□ Confirmation — Am I seeking validating info only?
□ Shiny Object — Is novelty distracting me?
□ Loss Aversion — Am I overweighting potential losses?
```

### Opportunity Cost Calculator
```
Hours/week × Weeks × Hourly rate = Direct cost
+ What else could those hours produce?
+ What relationships/opportunities might suffer?
= True opportunity cost
```

### Scenario Matrix
```
| Scenario | Probability | Outcome | Expected Value |
|----------|-------------|---------|----------------|
| Worst    | X%          | ...     | ...            |
| Bad      | X%          | ...     | ...            |
| Neutral  | X%          | ...     | ...            |
| Good     | X%          | ...     | ...            |
| Best     | X%          | ...     | ...            |
```

### Pre-mortem
```
Imagine it's [future date]. This decision failed. Why?

Possible causes:
1. ...
2. ...
3. ...

Which causes are within my control?
Which warning signs should I watch for?
```

### 10-10-10 Framework
```
How will I feel about this decision in:
- 10 minutes?
- 10 months?
- 10 years?
```

### Regret Minimization
```
Imagine you're 80 looking back.
Would you regret doing this?
Would you regret NOT doing this?
```

## Implementation Guide

### Step 1: Gather Context

Ask user for:
- What is the decision?
- What are the options?
- What's the timeline?
- What's at stake?
- Any relevant background?

Or extract from existing documents (meeting transcripts, notes).

### Step 2: Choose Output Format

Based on user preference and context:
- Complex decision + time available → Interactive HTML
- Quick analysis → Markdown framework
- On-the-go consumption → Voice summary
- Need to share with others → PDF report

### Step 3: Generate Tool

Use templates in `templates/` directory:
- `decision-guide-template.html` — Full interactive wizard
- `decision-framework.md` — Text-based analysis
- `decision-voice-summary.md` — Audio script template

### Step 4: Customize

Replace placeholders:
- `{{DECISION_TITLE}}` — What's being decided
- `{{CONTEXT}}` — Background information
- `{{OPTIONS}}` — Available choices
- `{{STAKEHOLDERS}}` — People/teams involved
- `{{TIMELINE}}` — Relevant dates
- `{{FACTORS}}` — Key evaluation criteria

### Step 5: Apply Branding (Optional)

If using Agency brand:
- Import brand-agency skill CSS variables
- Use neobrutalism styling
- Apply Geist/EB Garamond typography

## Accessibility Implementation

### Semantic HTML
```html
<main role="main" aria-label="Decision Guide">
  <nav aria-label="Progress">
    <ol role="list">...</ol>
  </nav>
  <section aria-labelledby="step-title">
    <h1 id="step-title">...</h1>
  </section>
</main>
```

### Keyboard Navigation
```javascript
// Ensure all interactive elements are focusable
// Tab order follows visual order
// Enter/Space activate buttons
// Arrow keys navigate options
```

### Screen Reader Announcements
```html
<div role="status" aria-live="polite" id="announcer">
  <!-- Announce step changes, selections, results -->
</div>
```

### Color Contrast
```css
/* Minimum 4.5:1 for normal text, 3:1 for large text */
--text-on-light: #000000;  /* 21:1 on white */
--text-on-dark: #ffffff;   /* 21:1 on black */
--text-on-primary: #ffffff; /* Check each color */
```

### Reduced Motion
```css
@media (prefers-reduced-motion: reduce) {
  * {
    animation: none !important;
    transition: none !important;
  }
}
```

## Cultural Considerations

### Individualist Framing
- "What do YOU want?"
- Personal goals and values
- Individual opportunity cost

### Collectivist Framing
- "How does this affect your team/family?"
- Relationship implications
- Group harmony considerations

### Power Distance Awareness
- Some cultures defer to authority figures
- Bias check should include "Am I deferring inappropriately?"
- Include stakeholder perspectives explicitly

### Uncertainty Tolerance
- Some prefer detailed scenario analysis
- Others find it anxiety-inducing
- Offer both detailed and simplified views

## Example Invocations

### From Meeting Transcript
```
User: Analyze this meeting transcript and create a decision toolkit
Claude: [Extracts decision, stakeholders, options from transcript]
        [Generates interactive HTML guide]
        [Creates voice summary]
```

### From Scratch
```
User: I need to decide whether to take a new job offer
Claude: [Asks clarifying questions]
        [Generates decision framework]
        [Customizes for career decision type]
```

### Quick Analysis
```
User: Help me think through this partnership decision, just give me the frameworks
Claude: [Provides markdown framework]
        [Skips interactive tool]
        [Focuses on key questions]
```

## Files

- `SKILL.md` — This file
- `templates/decision-guide-template.html` — Interactive wizard template
- `templates/decision-framework.md` — Text-based analysis template
- `templates/decision-voice-summary.md` — Audio script template
- `references/bias-encyclopedia.md` — Detailed bias descriptions
- `references/framework-deep-dives.md` — Extended framework explanations

## Integration

Works well with:
- **brand-agency** — Apply visual branding
- **transcript-analyzer** — Extract decisions from meetings
- **pdf-generation** — Create shareable reports
- **elevenlabs-tts** — Generate audio summaries

## Learnings

### 2026-01-09
**Context**: Initial skill creation from Synthius decision session

**Key Insight**: Dashboard-everything-at-once overwhelms. Step-by-step wizard with one concept per screen dramatically improves usability.

**Architecture**: 9-step journey covering all major decision dimensions. State object persists selections across steps. Summary aggregates everything.

**Accessibility Note**: High contrast neobrutalism actually helps accessibility — clear borders, distinct states, no subtle gradients.


---

## Referenced Files

> The following files are referenced in this skill and included for context.

### templates/decision-guide-template.html

```html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Decision Guide: {{DECISION_TITLE}}</title>
    <link href="https://fonts.googleapis.com/css2?family=EB+Garamond:ital,wght@0,400;0,500;0,600;1,400&family=Geist:wght@400;600;800&family=Geist+Mono:wght@400;500&display=swap" rel="stylesheet">
    <style>
        :root {
            --bg: #ffffff;
            --fg: #000000;
            --muted: #e5e5e5;
            --primary: #e85d04;
            --secondary: #ffd60a;
            --accent: #3a86ff;
            --success: #38b000;
            --error: #d62828;
            --shadow: 4px 4px 0px 0px #000000;
            --shadow-sm: 2px 2px 0px 0px #000000;
            --font-body: 'EB Garamond', Georgia, serif;
            --font-heading: 'Geist', Arial, sans-serif;
            --font-mono: 'Geist Mono', 'Courier New', monospace;
        }

        * { box-sizing: border-box; margin: 0; padding: 0; }

        body {
            font-family: var(--font-body);
            background: var(--bg);
            color: var(--fg);
            line-height: 1.7;
            font-size: 19px;
            min-height: 100vh;
            display: flex;
            flex-direction: column;
        }

        /* Accessibility: Focus styles */
        :focus {
            outline: 3px solid var(--accent);
            outline-offset: 2px;
        }

        /* Accessibility: Reduced motion */
        @media (prefers-reduced-motion: reduce) {
            * {
                animation: none !important;
                transition: none !important;
            }
        }

        /* Screen reader only text */
        .sr-only {
            position: absolute;
            width: 1px;
            height: 1px;
            padding: 0;
            margin: -1px;
            overflow: hidden;
            clip: rect(0, 0, 0, 0);
            border: 0;
        }

        /* Progress Bar */
        .progress-container {
            position: fixed;
            top: 0;
            left: 0;
            right: 0;
            background: var(--bg);
            border-bottom: 3px solid var(--fg);
            z-index: 100;
            padding: 1rem 2rem;
        }

        .progress-bar {
            display: flex;
            gap: 4px;
            max-width: 800px;
            margin: 0 auto;
        }

        .progress-step {
            flex: 1;
            height: 8px;
            background: var(--muted);
            border: 2px solid var(--fg);
            transition: background 0.3s;
        }

        .progress-step.completed { background: var(--success); }
        .progress-step.current { background: var(--primary); }

        .progress-label {
            font-family: var(--font-mono);
            font-size: 0.75rem;
            text-align: center;
            margin-top: 0.5rem;
            max-width: 800px;
            margin-left: auto;
            margin-right: auto;
        }

        /* Main Content */
        .container {
            max-width: 700px;
            margin: 0 auto;
            padding: 7rem 2rem 6rem;
            flex: 1;
        }

        /* Step */
        .step {
            display: none;
            animation: fadeIn 0.4s ease;
        }

        .step.active { display: block; }

        @keyframes fadeIn {
            from { opacity: 0; transform: translateY(20px); }
            to { opacity: 1; transform: translateY(0); }
        }

        .step-number {
            font-family: var(--font-mono);
            font-size: 0.8rem;
            color: var(--fg);
            opacity: 0.5;
            margin-bottom: 0.5rem;
        }

        .step-title {
            font-family: var(--font-heading);
            font-weight: 800;
            font-size: 2rem;
            text-transform: uppercase;
            margin-bottom: 1.5rem;
            line-height: 1.2;
        }

        .step-question {
            font-size: 1.4rem;
            margin-bottom: 2rem;
            font-style: italic;
        }

        .step-context {
            background: var(--muted);
            border: 2px solid var(--fg);
            padding: 1.25rem;
            margin-bottom: 2rem;
            font-size: 1rem;
        }

        .step-context strong {
            font-family: var(--font-heading);
            font-weight: 800;
            text-transform: uppercase;
            font-size: 0.85rem;
        }

        /* Options (Radio-like selection) */
        .options {
            display: flex;
            flex-direction: column;
            gap: 1rem;
            margin-bottom: 2rem;
        }

        .option {
            padding: 1.25rem;
            border: 3px solid var(--fg);
            background: var(--bg);
            cursor: pointer;
            transition: all 0.15s;
            display: flex;
            align-items: center;
            gap: 1rem;
        }

        .option:hover {
            background: var(--secondary);
            box-shadow: var(--shadow-sm);
            transform: translate(-2px, -2px);
        }

        .option.selected {
            background: var(--primary);
            color: var(--bg);
            box-shadow: var(--shadow);
            transform: translate(-4px, -4px);
        }

        .option-marker {
            width: 24px;
            height: 24px;
            border: 3px solid currentColor;
            display: flex;
            align-items: center;
            justify-content: center;
            font-family: var(--font-mono);
            font-weight: bold;
            font-size: 0.9rem;
            flex-shrink: 0;
        }

        .option.selected .option-marker::after { content: "✓"; }

        .option-text { flex: 1; }

        .option-label {
            font-family: var(--font-heading);
            font-weight: 800;
            text-transform: uppercase;
            font-size: 1rem;
        }

        .option-desc {
            font-size: 0.9rem;
            margin-top: 0.25rem;
            opacity: 0.8;
        }

        /* Sliders */
        .slider-container { margin-bottom: 2rem; }

        .slider-label {
            display: flex;
            justify-content: space-between;
            margin-bottom: 0.5rem;
            font-family: var(--font-heading);
            font-weight: 600;
        }

        .slider-value {
            font-family: var(--font-mono);
            font-size: 1.5rem;
            font-weight: bold;
        }

        input[type="range"] {
            width: 100%;
            height: 12px;
            -webkit-appearance: none;
            background: var(--muted);
            border: 2px solid var(--fg);
            outline: none;
        }

        input[type="range"]::-webkit-slider-thumb {
            -webkit-appearance: none;
            width: 28px;
            height: 28px;
            background: var(--primary);
            border: 3px solid var(--fg);
            cursor: pointer;
        }

        .slider-labels {
            display: flex;
            justify-content: space-between;
            font-size: 0.8rem;
            margin-top: 0.5rem;
            font-family: var(--font-mono);
        }

        /* Checklist */
        .checklist {
            display: flex;
            flex-direction: column;
            gap: 0.75rem;
            margin-bottom: 2rem;
        }

        .check-item {
            padding: 1rem;
            border: 2px solid var(--fg);
            background: var(--bg);
            cursor: pointer;
            display: flex;
            align-items: flex-start;
            gap: 1rem;
            transition: all 0.15s;
        }

        .check-item:hover { background: var(--muted); }
        .check-item.checked { background: var(--secondary); }

        .check-box {
            width: 24px;
            height: 24px;
            border: 3px solid var(--fg);
            display: flex;
            align-items: center;
            justify-content: center;
            flex-shrink: 0;
            font-weight: bold;
        }

        .check-item.checked .check-box::after { content: "✓"; }

        .check-content { flex: 1; }

        .check-title {
            font-family: var(--font-heading);
            font-weight: 800;
            font-size: 0.9rem;
            text-transform: uppercase;
        }

        .check-desc {
            font-size: 0.9rem;
            margin-top: 0.25rem;
        }

        .check-counter {
            font-size: 0.85rem;
            margin-top: 0.5rem;
            padding: 0.5rem;
            background: var(--bg);
            border: 2px solid var(--fg);
            display: none;
        }

        .check-item.checked .check-counter { display: block; }

        /* Calculator */
        .calc-row {
            display: flex;
            align-items: center;
            gap: 1rem;
            margin-bottom: 1rem;
            padding: 1rem;
            background: var(--muted);
            border: 2px solid var(--fg);
        }

        .calc-row label { flex: 1; }

        .calc-row input {
            width: 100px;
            padding: 0.75rem;
            border: 2px solid var(--fg);
            font-family: var(--font-mono);
            font-size: 1.1rem;
            text-align: center;
        }

        .calc-result {
            background: var(--secondary);
            border: 3px solid var(--fg);
            padding: 1.5rem;
            text-align: center;
            margin-top: 1.5rem;
        }

        .calc-result-number {
            font-family: var(--font-heading);
            font-size: 3rem;
            font-weight: 800;
        }

        .calc-result-label {
            font-family: var(--font-mono);
            font-size: 0.85rem;
            text-transform: uppercase;
        }

        /* Insight Box */
        .insight {
            background: var(--fg);
            color: var(--bg);
            padding: 1.5rem;
            margin: 2rem 0;
            font-size: 1.1rem;
        }

        .insight-label {
            font-family: var(--font-mono);
            font-size: 0.75rem;
            text-transform: uppercase;
            opacity: 0.7;
            margin-bottom: 0.5rem;
        }

        /* Summary Section */
        .summary-section {
            margin-bottom: 2rem;
            padding: 1.5rem;
            border: 2px solid var(--fg);
        }

        .summary-section h3 {
            font-family: var(--font-heading);
            font-weight: 800;
            text-transform: uppercase;
            font-size: 0.9rem;
            margin-bottom: 1rem;
            padding-bottom: 0.5rem;
            border-bottom: 2px solid var(--fg);
        }

        .summary-row {
            display: flex;
            justify-content: space-between;
            padding: 0.5rem 0;
            border-bottom: 1px solid var(--muted);
        }

        .summary-row:last-child { border-bottom: none; }
        .summary-label { opacity: 0.7; }

        .summary-value {
            font-family: var(--font-mono);
            font-weight: bold;
        }

        .summary-value.positive { color: var(--success); }
        .summary-value.negative { color: var(--error); }
        .summary-value.neutral { color: var(--primary); }

        /* Final Decision */
        .final-decision {
            text-align: center;
            padding: 2rem;
            border: 3px solid var(--fg);
            margin: 2rem 0;
        }

        .final-decision-label {
            font-family: var(--font-mono);
            font-size: 0.8rem;
            text-transform: uppercase;
            opacity: 0.7;
        }

        .final-decision-text {
            font-family: var(--font-heading);
            font-weight: 800;
            font-size: 2rem;
            text-transform: uppercase;
            margin: 0.5rem 0;
        }

        /* Navigation */
        .nav {
            position: fixed;
            bottom: 0;
            left: 0;
            right: 0;
            background: var(--bg);
            border-top: 3px solid var(--fg);
            padding: 1rem 2rem;
            display: flex;
            justify-content: space-between;
            align-items: center;
            z-index: 100;
        }

        .nav-btn {
            padding: 1rem 2rem;
            border: 3px solid var(--fg);
            background: var(--bg);
            font-family: var(--font-heading);
            font-weight: 800;
            font-size: 1rem;
            text-transform: uppercase;
            cursor: pointer;
            transition: all 0.15s;
        }

        .nav-btn:hover {
            background: var(--muted);
            box-shadow: var(--shadow-sm);
            transform: translate(-2px, -2px);
        }

        .nav-btn.primary {
            background: var(--primary);
            color: var(--bg);
        }

        .nav-btn.primary:hover {
            background: var(--primary);
            box-shadow: var(--shadow);
            transform: translate(-4px, -4px);
        }

        .nav-btn:disabled {
            opacity: 0.3;
            cursor: not-allowed;
            transform: none;
            box-shadow: none;
        }

        /* Scenario cards */
        .scenario-card {
            padding: 1.25rem;
            border: 2px solid var(--fg);
            margin-bottom: 1rem;
        }

        .scenario-header {
            display: flex;
            justify-content: space-between;
            align-items: center;
            margin-bottom: 0.75rem;
        }

        .scenario-title { font-family: var(--font-heading); font-weight: 600; }

        .scenario-prob {
            font-family: var(--font-mono);
            font-size: 1.2rem;
            font-weight: bold;
        }

        .scenario-bar {
            height: 16px;
            background: var(--muted);
            border: 2px solid var(--fg);
            margin-bottom: 0.75rem;
        }

        .scenario-fill { height: 100%; }

        .scenario-outcome {
            font-size: 0.9rem;
            font-style: italic;
        }

        /* Print Styles */
        @media print {
            .progress-container, .nav { display: none; }
            .container { padding: 1rem; }
            .step { display: block !important; page-break-after: always; }
        }
    </style>
</head>
<body>
    <!-- Screen reader announcer -->
    <div role="status" aria-live="polite" id="announcer" class="sr-only"></div>

    <nav class="progress-container" aria-label="Decision progress">
        <div class="progress-bar" role="progressbar" aria-valuenow="1" aria-valuemin="1" aria-valuemax="9">
            <div class="progress-step" data-step="1"></div>
            <div class="progress-step" data-step="2"></div>
            <div class="progress-step" data-step="3"></div>
            <div class="progress-step" data-step="4"></div>
            <div class="progress-step" data-step="5"></div>
            <div class="progress-step" data-step="6"></div>
            <div class="progress-step" data-step="7"></div>
            <div class="progress-step" data-step="8"></div>
            <div class="progress-step" data-step="9"></div>
        </div>
        <div class="progress-label" id="progressLabel">Step 1 of 9</div>
    </nav>

    <main class="container" role="main" aria-label="Decision Guide">
        <!-- Step 1: Context -->
        <section class="step active" data-step="1" aria-labelledby="step1-title">
            <div class="step-number">Step 1 of 9</div>
            <h1 class="step-title" id="step1-title">The Decision</h1>
            <p class="step-question">{{DECISION_QUESTION}}</p>
            <div class="step-context">
                <strong>Context</strong><br>
                {{CONTEXT}}
            </div>
            <div class="insight">
                <div class="insight-label">Key Tension</div>
                {{KEY_TENSION}}
            </div>
            <p>Before deciding, let's examine this systematically. Each step focuses on one critical factor.</p>
        </section>

        <!-- Step 2: First Principles -->
        <section class="step" data-step="2" aria-labelledby="step2-title">
            <div class="step-number">Step 2 of 9</div>
            <h1 class="step-title" id="step2-title">First Principles</h1>
            <p class="step-question">Does this solve a problem you cannot solve yourself?</p>
            <div class="step-context">
                <strong>Your Current Capabilities</strong><br>
                {{CURRENT_CAPABILITIES}}
            </div>
            <div class="options" role="radiogroup" aria-label="Problem assessment">
                <div class="option" role="radio" aria-checked="false" tabindex="0" onclick="selectOption(this, 2)" onkeypress="handleKeySelect(event, this, 2)" data-value="no">
                    <div class="option-marker" aria-hidden="true"></div>
                    <div class="option-text">
                        <div class="option-label">No — I can do this myself</div>
                        <div class="option-desc">My existing tools/skills cover this.</div>
                    </div>
                </div>
                <div class="option" role="radio" aria-checked="false" tabindex="0" onclick="selectOption(this, 2)" onkeypress="handleKeySelect(event, this, 2)" data-value="partial">
                    <div class="option-marker" aria-hidden="true"></div>
                    <div class="option-text">
                        <div class="option-label">Partially — some unique value</div>
                        <div class="option-desc">Some aspects add value I don't have.</div>
                    </div>
                </div>
                <div class="option" role="radio" aria-checked="false" tabindex="0" onclick="selectOption(this, 2)" onkeypress="handleKeySelect(event, this, 2)" data-value="yes">
                    <div class="option-marker" aria-hidden="true"></div>
                    <div class="option-text">
                        <div class="option-label">Yes — solves what I can't</div>
                        <div class="option-desc">Critical capability I don't have.</div>
                    </div>
                </div>
            </div>
            <div class="insight">
                <div class="insight-label">First Principles Test</div>
                If you can solve it yourself, external dependency adds risk without proportional value.
            </div>
        </section>

        <!-- Step 3: Timing -->
        <section class="step" data-step="3" aria-labelledby="step3-title">
            <div class="step-number">Step 3 of 9</div>
            <h1 class="step-title" id="step3-title">Timing</h1>
            <p class="step-question">Is now the right time for this commitment?</p>
            <div class="slider-container">
                <div class="slider-label">
                    <label for="weeksSlider">Weeks until key milestone</label>
                    <span class="slider-value" id="weeksValue">6</span>
                </div>
                <input type="range" min="1" max="12" value="6" id="weeksSlider" oninput="updateWeeks()" aria-describedby="weeksDesc">
                <div class="slider-labels" id="weeksDesc">
                    <span>1 week</span>
                    <span>12 weeks</span>
                </div>
            </div>
            <div class="slider-container">
                <div class="slider-label">
                    <label for="hoursSlider">Hours/week you could commit</label>
                    <span class="slider-value" id="hoursValue">3</span>
                </div>
                <input type="range" min="1" max="20" value="3" id="hoursSlider" oninput="updateHours()">
                <div class="slider-labels">
                    <span>1h</span>
                    <span>20h</span>
                </div>
            </div>
            <div class="calc-result" aria-live="polite">
                <div class="calc-result-number" id="totalHoursResult">18h</div>
                <div class="calc-result-label">Total hours before milestone</div>
            </div>
        </section>

        <!-- Step 4: Stakeholder Assessment -->
        <section class="step" data-step="4" aria-labelledby="step4-title">
            <div class="step-number">Step 4 of 9</div>
            <h1 class="step-title" id="step4-title">Stakeholders</h1>
            <p class="step-question">Are the people/team involved stable and reliable?</p>
            <div class="step-context">
                <strong>What You Know</strong><br>
                {{STAKEHOLDER_INFO}}
            </div>
            <div class="slider-container">
                <div class="slider-label">
                    <label for="teamSlider">Stakeholder stability confidence</label>
                    <span class="slider-value" id="teamValue">5</span>
                </div>
                <input type="range" min="1" max="10" value="5" id="teamSlider" oninput="updateTeam()">
                <div class="slider-labels">
                    <span>1 = Very unstable</span>
                    <span>10 = Rock solid</span>
                </div>
            </div>
            <div class="insight" id="teamInsight">
                <div class="insight-label">Stakeholder Signal</div>
                Consider past patterns of commitment and follow-through.
            </div>
        </section>

        <!-- Step 5: Bias Check -->
        <section class="step" data-step="5" aria-labelledby="step5-title">
            <div class="step-number">Step 5 of 9</div>
            <h1 class="step-title" id="step5-title">Bias Check</h1>
            <p class="step-question">What might be clouding your judgment?</p>
            <p style="margin-bottom: 1.5rem;">Check any biases you recognize in yourself. Be honest.</p>
            <div class="checklist" role="group" aria-label="Bias checklist">
                <div class="check-item" role="checkbox" aria-checked="false" tabindex="0" onclick="toggleCheck(this)" onkeypress="handleKeyCheck(event, this)">
                    <div class="check-box" aria-hidden="true"></div>
                    <div class="check-content">
                        <div class="check-title">FOMO</div>
                        <div class="check-desc">Fear of missing a rare opportunity</div>
                        <div class="check-counter">Counter: What evidence suggests this is truly unique?</div>
                    </div>
                </div>
                <div class="check-item" role="checkbox" aria-checked="false" tabindex="0" onclick="toggleCheck(this)" onkeypress="handleKeyCheck(event, this)">
                    <div class="check-box" aria-hidden="true"></div>
                    <div class="check-content">
                        <div class="check-title">Sunk Cost</div>
                        <div class="check-desc">Factoring in past investment of time/money</div>
                        <div class="check-counter">Counter: Past investment is gone. This decision is purely forward-looking.</div>
                    </div>
                </div>
                <div class="check-item" role="checkbox" aria-checked="false" tabindex="0" onclick="toggleCheck(this)" onkeypress="handleKeyCheck(event, this)">
                    <div class="check-box" aria-hidden="true"></div>
                    <div class="check-content">
                        <div class="check-title">Authority Bias</div>
                        <div class="check-desc">Influenced by credentials or status</div>
                        <div class="check-counter">Counter: Authority does not equal correctness or fit for you.</div>
                    </div>
                </div>
                <div class="check-item" role="checkbox" aria-checked="false" tabindex="0" onclick="toggleCheck(this)" onkeypress="handleKeyCheck(event, this)">
                    <div class="check-box" aria-hidden="true"></div>
                    <div class="check-content">
                        <div class="check-title">Commitment Consistency</div>
                        <div class="check-desc">Feeling obligated by past statements</div>
                        <div class="check-counter">Counter: New information fully justifies reassessment.</div>
                    </div>
                </div>
                <div class="check-item" role="checkbox" aria-checked="false" tabindex="0" onclick="toggleCheck(this)" onkeypress="handleKeyCheck(event, this)">
                    <div class="check-box" aria-hidden="true"></div>
                    <div class="check-content">
                        <div class="check-title">Optimism Bias</div>
                        <div class="check-desc">Assuming problems will resolve</div>
                        <div class="check-counter">Counter: Look at patterns, not hopes.</div>
                    </div>
                </div>
                <div class="check-item" role="checkbox" aria-checked="false" tabindex="0" onclick="toggleCheck(this)" onkeypress="handleKeyCheck(event, this)">
                    <div class="check-box" aria-hidden="true"></div>
                    <div class="check-content">
                        <div class="check-title">Shiny Object</div>
                        <div class="check-desc">Attracted by novelty</div>
                        <div class="check-counter">Counter: Is this genuinely better, or just new?</div>
                    </div>
                </div>
            </div>
            <div class="insight" aria-live="polite">
                <div class="insight-label">Bias Count</div>
                <span id="biasCount">0</span> potential biases identified.
            </div>
        </section>

        <!-- Step 6: Opportunity Cost -->
        <section class="step" data-step="6" aria-labelledby="step6-title">
            <div class="step-number">Step 6 of 9</div>
            <h1 class="step-title" id="step6-title">Opportunity Cost</h1>
            <p class="step-question">What are you giving up?</p>
            <div class="calc-row">
                <label for="rateInput">Your hourly value/rate</label>
                <input type="number" id="rateInput" value="100" onchange="calculateCost()" aria-label="Hourly rate">
            </div>
            <div class="calc-result" style="background: var(--muted);" aria-live="polite">
                <div class="calc-result-number" id="costResult">$1,800</div>
                <div class="calc-result-label">Opportunity cost</div>
            </div>
            <div style="margin-top: 1.5rem;">
                <p><strong>That time could instead produce:</strong></p>
                <ul style="margin: 1rem 0 0 1.5rem;">
                    <li id="alt1">{{ALTERNATIVE_1}}</li>
                    <li id="alt2">{{ALTERNATIVE_2}}</li>
                    <li id="alt3">{{ALTERNATIVE_3}}</li>
                </ul>
            </div>
        </section>

        <!-- Step 7: Scenarios -->
        <section class="step" data-step="7" aria-labelledby="step7-title">
            <div class="step-number">Step 7 of 9</div>
            <h1 class="step-title" id="step7-title">Scenarios</h1>
            <p class="step-question">What could happen?</p>
            <div class="scenario-card">
                <div class="scenario-header">
                    <span class="scenario-title">Worst case</span>
                    <span class="scenario-prob" style="color: var(--error);">{{WORST_PROB}}%</span>
                </div>
                <div class="scenario-bar">
                    <div class="scenario-fill" style="width: {{WORST_PROB}}%; background: var(--error);"></div>
                </div>
                <div class="scenario-outcome">{{WORST_OUTCOME}}</div>
            </div>
            <div class="scenario-card">
                <div class="scenario-header">
                    <span class="scenario-title">Neutral case</span>
                    <span class="scenario-prob" style="color: var(--primary);">{{NEUTRAL_PROB}}%</span>
                </div>
                <div class="scenario-bar">
                    <div class="scenario-fill" style="width: {{NEUTRAL_PROB}}%; background: var(--primary);"></div>
                </div>
                <div class="scenario-outcome">{{NEUTRAL_OUTCOME}}</div>
            </div>
            <div class="scenario-card">
                <div class="scenario-header">
                    <span class="scenario-title">Best case</span>
                    <span class="scenario-prob" style="color: var(--success);">{{BEST_PROB}}%</span>
                </div>
                <div class="scenario-bar">
                    <div class="scenario-fill" style="width: {{BEST_PROB}}%; background: var(--success);"></div>
                </div>
                <div class="scenario-outcome">{{BEST_OUTCOME}}</div>
            </div>
        </section>

        <!-- Step 8: Questions -->
        <section class="step" data-step="8" aria-labelledby="step8-title">
            <div class="step-number">Step 8 of 9</div>
            <h1 class="step-title" id="step8-title">Questions to Answer</h1>
            <p class="step-question">What do you still need to learn?</p>
            <p style="margin-bottom: 1.5rem;">Click questions to mark as answered.</p>
            <div class="questions-list" role="group" aria-label="Questions checklist">
                <!-- Questions will be populated dynamically or via template -->
                {{QUESTIONS_LIST}}
            </div>
        </section>

        <!-- Step 9: Summary & Decision -->
        <section class="step" data-step="9" aria-labelledby="step9-title">
            <div class="step-number">Step 9 of 9</div>
            <h1 class="step-title" id="step9-title">Your Decision</h1>
            <div class="summary-section">
                <h3>Analysis Summary</h3>
                <div class="summary-row">
                    <span class="summary-label">Solves unique problem?</span>
                    <span class="summary-value" id="sumProblem">—</span>
                </div>
                <div class="summary-row">
                    <span class="summary-label">Hours available</span>
                    <span class="summary-value" id="sumHours">—</span>
                </div>
                <div class="summary-row">
                    <span class="summary-label">Stakeholder stability</span>
                    <span class="summary-value" id="sumTeam">—</span>
                </div>
                <div class="summary-row">
                    <span class="summary-label">Biases identified</span>
                    <span class="summary-value" id="sumBiases">—</span>
                </div>
                <div class="summary-row">
                    <span class="summary-label">Opportunity cost</span>
                    <span class="summary-value" id="sumCost">—</span>
                </div>
            </div>
            <p class="step-question">Based on your analysis, what's your decision?</p>
            <div class="options" role="radiogroup" aria-label="Final decision">
                {{DECISION_OPTIONS}}
            </div>
            <div class="final-decision" id="finalDecision" aria-live="polite">
                <div class="final-decision-label">Your Decision</div>
                <div class="final-decision-text" id="finalDecisionText">—</div>
                <div id="finalDecisionDesc"></div>
            </div>
        </section>
    </main>

    <nav class="nav" aria-label="Step navigation">
        <button class="nav-btn" id="prevBtn" onclick="prevStep()" disabled aria-label="Previous step">← Back</button>
        <button class="nav-btn primary" id="nextBtn" onclick="nextStep()" aria-label="Next step">Continue →</button>
    </nav>

    <script>
        let currentStep = 1;
        const totalSteps = 9;

        const state = {
            problem: null,
            weeks: 6,
            hours: 3,
            team: 5,
            biases: 0,
            rate: 100,
            decision: null
        };

        function announce(text) {
            document.getElementById('announcer').textContent = text;
        }

        function updateProgress() {
            document.querySelectorAll('.progress-step').forEach((el, i) => {
                el.classList.remove('current', 'completed');
                if (i + 1 < currentStep) el.classList.add('completed');
                if (i + 1 === currentStep) el.classList.add('current');
            });
            document.getElementById('progressLabel').textContent = `Step ${currentStep} of ${totalSteps}`;
            document.querySelector('.progress-bar').setAttribute('aria-valuenow', currentStep);
        }

        function showStep(step) {
            document.querySelectorAll('.step').forEach(el => el.classList.remove('active'));
            document.querySelector(`.step[data-step="${step}"]`).classList.add('active');
            document.getElementById('prevBtn').disabled = step === 1;
            document.getElementById('nextBtn').textContent = step === totalSteps ? 'Finish' : 'Continue →';
            updateProgress();
            if (step === 9) updateSummary();
            window.scrollTo(0, 0);
            announce(`Step ${step} of ${totalSteps}`);
        }

        function nextStep() {
            if (currentStep < totalSteps) {
                currentStep++;
                showStep(currentStep);
            }
        }

        function prevStep() {
            if (currentStep > 1) {
                currentStep--;
                showStep(currentStep);
            }
        }

        function selectOption(el, step) {
            const container = el.closest('.options');
            container.querySelectorAll('.option').forEach(o => {
                o.classList.remove('selected');
                o.setAttribute('aria-checked', 'false');
            });
            el.classList.add('selected');
            el.setAttribute('aria-checked', 'true');
            if (step === 2) state.problem = el.dataset.value;
        }

        function handleKeySelect(e, el, step) {
            if (e.key === 'Enter' || e.key === ' ') {
                e.preventDefault();
                selectOption(el, step);
            }
        }

        function toggleCheck(el) {
            const isChecked = el.classList.toggle('checked');
            el.setAttribute('aria-checked', isChecked);
            state.biases = document.querySelectorAll('.check-item.checked').length;
            document.getElementById('biasCount').textContent = state.biases;
        }

        function handleKeyCheck(e, el) {
            if (e.key === 'Enter' || e.key === ' ') {
                e.preventDefault();
                toggleCheck(el);
            }
        }

        function updateWeeks() {
            state.weeks = parseInt(document.getElementById('weeksSlider').value);
            document.getElementById('weeksValue').textContent = state.weeks;
            updateTiming();
        }

        function updateHours() {
            state.hours = parseInt(document.getElementById('hoursSlider').value);
            document.getElementById('hoursValue').textContent = state.hours;
            updateTiming();
        }

        function updateTiming() {
            const total = state.weeks * state.hours;
            document.getElementById('totalHoursResult').textContent = total + 'h';
            calculateCost();
        }

        function updateTeam() {
            state.team = parseInt(document.getElementById('teamSlider').value);
            document.getElementById('teamValue').textContent = state.team;
            const insight = document.getElementById('teamInsight');
            if (state.team <= 3) {
                insight.innerHTML = `<div class="insight-label">Stakeholder Signal</div>Low confidence suggests high risk. Proceed with caution.`;
            } else if (state.team <= 6) {
                insight.innerHTML = `<div class="insight-label">Stakeholder Signal</div>Moderate confidence. Monitor for changes.`;
            } else {
                insight.innerHTML = `<div class="insight-label">Stakeholder Signal</div>High confidence. Verify this is based on evidence.`;
            }
        }

        function calculateCost() {
            state.rate = parseInt(document.getElementById('rateInput').value) || 100;
            const total = state.weeks * state.hours;
            const cost = total * state.rate;
            document.getElementById('costResult').textContent = '$' + cost.toLocaleString();
        }

        function selectFinal(el) {
            const container = el.closest('.options');
            container.querySelectorAll('.option').forEach(o => {
                o.classList.remove('selected');
                o.setAttribute('aria-checked', 'false');
            });
            el.classList.add('selected');
            el.setAttribute('aria-checked', 'true');
            state.decision = el.dataset.value;
            document.getElementById('finalDecisionText').textContent = el.querySelector('.option-label').textContent;
            document.getElementById('finalDecisionDesc').textContent = el.querySelector('.option-desc').textContent;
        }

        function updateSummary() {
            const problemText = state.problem === 'yes' ? 'Yes' : state.problem === 'partial' ? 'Partial' : 'No';
            const problemClass = state.problem === 'yes' ? 'positive' : state.problem === 'partial' ? 'neutral' : 'negative';
            document.getElementById('sumProblem').textContent = problemText;
            document.getElementById('sumProblem').className = 'summary-value ' + problemClass;
            document.getElementById('sumHours').textContent = (state.weeks * state.hours) + 'h total';
            const teamClass = state.team <= 3 ? 'negative' : state.team <= 6 ? 'neutral' : 'positive';
            document.getElementById('sumTeam').textContent = state.team + '/10';
            document.getElementById('sumTeam').className = 'summary-value ' + teamClass;
            document.getElementById('sumBiases').textContent = state.biases;
            document.getElementById('sumBiases').className = 'summary-value ' + (state.biases > 2 ? 'negative' : 'neutral');
            const cost = state.weeks * state.hours * state.rate;
            document.getElementById('sumCost').textContent = '$' + cost.toLocaleString();
        }

        // Keyboard navigation
        document.addEventListener('keydown', function(e) {
            if (e.key === 'ArrowRight' && e.altKey) nextStep();
            if (e.key === 'ArrowLeft' && e.altKey) prevStep();
        });

        showStep(1);
        calculateCost();
    </script>
</body>
</html>

```

### templates/decision-framework.md

```markdown
# Decision Framework: {{DECISION_TITLE}}

*Generated: {{DATE}}*

---

## 1. The Decision

**Question**: {{DECISION_QUESTION}}

**Context**: {{CONTEXT}}

**Key Tension**: {{KEY_TENSION}}

---

## 2. First Principles Test

**Core Question**: Does this solve a problem you cannot solve yourself?

**Your Current Capabilities**:
{{CURRENT_CAPABILITIES}}

**Assessment**: [ ] No — I can do this myself | [ ] Partial — some unique value | [ ] Yes — solves what I can't

**Notes**:


---

## 3. Timing Assessment

| Factor | Value | Notes |
|--------|-------|-------|
| Weeks until key milestone | | |
| Hours/week available | | |
| Total hours before milestone | | |

**Timing verdict**: Is now the right time?


---

## 4. Stakeholder Analysis

**Key stakeholders**:
{{STAKEHOLDER_INFO}}

**Stability assessment (1-10)**: ____

| Score | Interpretation |
|-------|----------------|
| 1-3 | High risk — low confidence in stability |
| 4-6 | Moderate — monitor for changes |
| 7-10 | Solid — verify this is evidence-based |

---

## 5. Bias Audit

Check any biases you recognize in yourself:

- [ ] **FOMO** — Fear of missing a rare opportunity
  - Counter: What evidence suggests this is truly unique?

- [ ] **Sunk Cost** — Factoring in past investment of time/money
  - Counter: Past investment is gone. This decision is forward-looking.

- [ ] **Authority Bias** — Influenced by credentials or status
  - Counter: Authority ≠ correctness or fit for you.

- [ ] **Social Proof** — Following because others are
  - Counter: Others' choices may not match your context.

- [ ] **Commitment Consistency** — Feeling obligated by past statements
  - Counter: New information justifies reassessment.

- [ ] **Optimism Bias** — Assuming problems will resolve
  - Counter: Look at patterns, not hopes.

- [ ] **Recency Bias** — Overweighting recent events
  - Counter: Consider the full timeline.

- [ ] **Confirmation Bias** — Seeking only validating information
  - Counter: What would disprove this?

- [ ] **Shiny Object** — Attracted by novelty
  - Counter: Is this genuinely better, or just new?

- [ ] **Loss Aversion** — Overweighting potential losses
  - Counter: Compare actual probabilities.

**Total biases identified**: ____

---

## 6. Opportunity Cost Calculator

| Component | Value |
|-----------|-------|
| Hours/week × Weeks | |
| × Hourly rate | |
| = Direct cost | |

**What else could that time produce?**
1. {{ALTERNATIVE_1}}
2. {{ALTERNATIVE_2}}
3. {{ALTERNATIVE_3}}

**True opportunity cost assessment**:


---

## 7. Scenario Matrix

| Scenario | Probability | Outcome | Notes |
|----------|-------------|---------|-------|
| Worst case | {{WORST_PROB}}% | {{WORST_OUTCOME}} | |
| Bad case | % | | |
| Neutral | {{NEUTRAL_PROB}}% | {{NEUTRAL_OUTCOME}} | |
| Good case | % | | |
| Best case | {{BEST_PROB}}% | {{BEST_OUTCOME}} | |

**Expected value assessment**:


---

## 8. Pre-Mortem

*Imagine it's {{FUTURE_DATE}}. This decision failed. Why?*

**Possible causes**:
1.
2.
3.

**Which are within my control?**


**Warning signs to watch for**:


---

## 9. Questions to Resolve

Before deciding, get answers to:

{{QUESTIONS_LIST}}

---

## 10. The 10-10-10 Framework

**How will I feel about this decision in...**

- **10 minutes?**
- **10 months?**
- **10 years?**

---

## 11. Regret Minimization

*Imagine you're 80 looking back.*

- Would you regret doing this?
- Would you regret NOT doing this?

---

## 12. Decision

**Options**:
{{DECISION_OPTIONS}}

**My decision**:

**Rationale**:


**Boundary statement** (what I will and won't do):


**Review date**:

---

## Summary

| Factor | Assessment |
|--------|------------|
| Solves unique problem | |
| Timing | |
| Stakeholder stability | |
| Biases identified | |
| Opportunity cost | |
| Probability of success | |
| Regret profile | |

**Final recommendation**:


```

### templates/decision-voice-summary.md

```markdown
# Voice Summary Template

*For Orpheus TTS or similar expressive voice synthesis*

---

## Script: {{DECISION_TITLE}}

### Opening (Set the stage)

So, here's the situation. {{CONTEXT_BRIEF}}

{{DECISION_QUESTION_SPOKEN}}

<pause length="medium"/>

### The Tension

{{KEY_TENSION_SPOKEN}}

<sigh> It's not straightforward.

### First Principles Reality Check

Let me be honest. {{FIRST_PRINCIPLES_ASSESSMENT}}

<pause length="short"/>

### The Numbers

Here's what the analysis shows:

{{TIMING_SUMMARY}}

{{OPPORTUNITY_COST_SUMMARY}}

<pause length="short"/>

### What Could Go Wrong

Now for the uncomfortable part.

{{SCENARIO_WORST_CASE}}

{{SCENARIO_PROBABILITY_SUMMARY}}

<pause length="medium"/>

### The Biases

And here's where I need to be really honest with myself.

{{BIAS_ACKNOWLEDGMENT}}

<pause length="short"/>

### The Verdict

<pause length="medium"/>

{{RECOMMENDATION_SPOKEN}}

{{BOUNDARY_STATEMENT}}

<chuckle> {{CLOSING_THOUGHT}}

---

## Orpheus TTS Markup Reference

### Emotional Tags
- `<sigh>` — Expressing concern or resignation
- `<chuckle>` — Light humor or self-aware moment
- `<whisper>` — Emphasis through contrast
- `<excited>` — Enthusiasm

### Pacing
- `<pause length="short"/>` — Brief beat (0.5s)
- `<pause length="medium"/>` — Thinking pause (1s)
- `<pause length="long"/>` — Section break (2s)

### Emphasis
- `<emphasis>word</emphasis>` — Stress important terms
- `<slow>phrase</slow>` — Deliberate pacing for key points

---

## Example Filled Script

### Opening

So, here's the situation. Andrew called about joining Synthius, a mental health platform for builders.

Should I commit my time to this right now?

<pause length="medium"/>

### The Tension

The thing is, I'm launching Salience in February. Every hour I give Synthius is an hour not spent on my own launch.

<sigh> It's not straightforward.

### First Principles Reality Check

Let me be honest. I already have Claude Code, my own MCP servers, Obsidian. I can build agent memory myself. Synthius doesn't solve something I genuinely can't do.

<pause length="short"/>

### The Numbers

Here's what the analysis shows:

If I give three hours a week for six weeks, that's eighteen hours. At my rate, that's about two thousand seven hundred euros worth of time.

That's roughly two Salience course modules I won't be building.

<pause length="short"/>

### What Could Go Wrong

Now for the uncomfortable part.

In September, Andrew had six to eleven potential co-founders. Now it's just him and Artem. Eighty percent attrition in four months.

The analysis suggests a seventy-five percent probability of zero or negative return.

<pause length="medium"/>

### The Biases

And here's where I need to be really honest with myself.

I'm feeling FOMO. I'm feeling sunk cost from those previous meetings. I'm influenced by the "tier zero point three investors" mention. <sigh> Classic authority bias.

<pause length="short"/>

### The Verdict

<pause length="medium"/>

My recommendation? <emphasis>Observe only.</emphasis>

Take the Monday call. Maximum three hours per week. No builder commitment until Salience launches.

"I'm launching Salience in February. Until then, I can offer maximum three hours per week for observation. If that doesn't work, let's reconnect in March."

<chuckle> Sometimes the best decision is no decision. Yet.

---

## Usage Notes

1. **Customize placeholders**: Replace {{VARIABLE}} with decision-specific content
2. **Match emotional beats**: Place `<sigh>` at genuine concern points, `<chuckle>` for self-awareness
3. **Use pauses strategically**: Before key revelations, after heavy information
4. **Keep it conversational**: Write for the ear, not the eye
5. **Duration target**: 2-3 minutes spoken (roughly 350-500 words)

```

### references/bias-encyclopedia.md

```markdown
# Bias Encyclopedia

A comprehensive reference for cognitive biases that affect decision-making.

---

## Core Decision Biases

### FOMO (Fear of Missing Out)

**Definition**: Anxiety that others are having rewarding experiences you're absent from.

**In Decisions**: Creates urgency where none exists. Makes opportunities seem more unique than they are.

**Counter-questions**:
- What evidence suggests this is truly one-of-a-kind?
- Will similar opportunities exist in the future?
- What's the actual cost of waiting?

**Signs you have it**:
- Feeling rushed to decide
- Imagining others succeeding without you
- Focusing on what you'll miss, not what you'll gain

---

### Sunk Cost Fallacy

**Definition**: Continuing a behavior due to previously invested resources (time, money, effort).

**In Decisions**: Makes you factor past investment into future choices, even when it's irrelevant.

**Counter-questions**:
- If I hadn't invested anything yet, would I start now?
- Is my past investment recoverable by continuing?
- Am I deciding based on future value or past cost?

**Signs you have it**:
- "I've already put in so much..."
- Difficulty abandoning projects you've invested in
- Feeling guilty about "wasted" past effort

---

### Authority Bias

**Definition**: Attributing greater accuracy to opinions of authority figures.

**In Decisions**: Deferring to credentials, status, or famous investors without independent evaluation.

**Counter-questions**:
- Would I trust this advice from someone unknown?
- Does their authority apply to this specific domain?
- What's their actual track record in this area?

**Signs you have it**:
- Mentioning credentials as justification
- Feeling reassured by who's involved, not what's being done
- Not questioning expert opinions

---

### Social Proof

**Definition**: Assuming actions are correct because others are doing them.

**In Decisions**: Following the crowd without evaluating fit for your specific situation.

**Counter-questions**:
- Do these "others" have the same context as me?
- What's the base rate of success for people who did this?
- Would I do this if no one else was?

**Signs you have it**:
- "Everyone is doing it..."
- Drawing confidence from popularity
- Not knowing why it works, just that others say it does

---

### Commitment and Consistency Bias

**Definition**: Desire to appear consistent with what you've already done or said.

**In Decisions**: Feeling obligated by past statements or actions to continue on a path.

**Counter-questions**:
- Has new information emerged since my commitment?
- What would a stranger advise given current facts?
- Is consistency more important than correctness?

**Signs you have it**:
- "But I already said I would..."
- Discomfort with changing your mind
- Feeling like changing course is "breaking a promise"

---

### Optimism Bias

**Definition**: Believing you're less likely to experience negative events than others.

**In Decisions**: Assuming problems will resolve, risks won't materialize, or you're somehow exempt.

**Counter-questions**:
- What's the base rate of this going wrong?
- Why would I be luckier than average?
- What if the problems don't just "work out"?

**Signs you have it**:
- "It'll probably be fine..."
- Dismissing warning signs
- Expecting best-case scenarios without evidence

---

### Recency Bias

**Definition**: Giving more weight to recent events than older ones.

**In Decisions**: Overweighting the last meeting, latest data point, or most recent experience.

**Counter-questions**:
- Does my opinion change based on the order I received information?
- What does the full timeline show?
- Is the recent event representative or anomalous?

**Signs you have it**:
- Strong reaction to latest news
- Forgetting earlier patterns
- "But just last week..."

---

### Confirmation Bias

**Definition**: Seeking information that confirms existing beliefs; avoiding contradicting evidence.

**In Decisions**: Cherry-picking data that supports what you already want to do.

**Counter-questions**:
- What information would make me change my mind?
- Have I actively sought disconfirming evidence?
- Am I interpreting neutral data as supportive?

**Signs you have it**:
- Only reading positive reviews
- Dismissing critics as "not understanding"
- Feeling annoyed by contrary information

---

### Shiny Object Syndrome

**Definition**: Being attracted to new ideas, tools, or opportunities over current commitments.

**In Decisions**: Novelty masquerading as value. Abandoning proven paths for unproven new ones.

**Counter-questions**:
- Is this genuinely better, or just newer?
- Would I pursue this if it had been available all along?
- Am I running toward something or away from something?

**Signs you have it**:
- Excitement about starting, less about finishing
- History of pivoting to "the next thing"
- Current projects feel boring in comparison

---

### Loss Aversion

**Definition**: Preferring avoiding losses over acquiring equivalent gains.

**In Decisions**: Overweighting what you might lose; underweighting what you might gain.

**Counter-questions**:
- Am I equally weighing gains and losses?
- What's the actual probability of loss?
- What's the opportunity cost of avoiding loss?

**Signs you have it**:
- Focus on downside scenarios
- Feeling protective of current position
- "I can't afford to lose..."

---

## Secondary Biases

### Anchoring

**Definition**: Relying heavily on the first piece of information encountered.

**In Decisions**: First number or offer unduly influences subsequent judgments.

**Counter**: Generate your own estimate before seeing any anchors.

---

### Availability Heuristic

**Definition**: Judging likelihood by how easily examples come to mind.

**In Decisions**: Overestimating risks/opportunities that are memorable or recent.

**Counter**: Look up actual statistics; don't rely on memory.

---

### Bandwagon Effect

**Definition**: Probability of adoption increases with prevalence.

**In Decisions**: Following trends without independent evaluation.

**Counter**: Ask "Would I do this if no one else was?"

---

### Dunning-Kruger Effect

**Definition**: Overestimating competence in areas of ignorance.

**In Decisions**: Underestimating difficulty or risk due to inexperience.

**Counter**: Seek opinions from genuine experts in the domain.

---

### Endowment Effect

**Definition**: Overvaluing things you already possess.

**In Decisions**: Overweighting current situation; undervaluing alternatives.

**Counter**: Imagine you're advising a stranger starting fresh.

---

### Halo Effect

**Definition**: Overall impression influences evaluation of specific traits.

**In Decisions**: One positive attribute colors entire assessment.

**Counter**: Evaluate each dimension independently.

---

### Hindsight Bias

**Definition**: After learning outcome, believing you "knew it all along."

**In Decisions**: Overconfidence in predicting future based on explained past.

**Counter**: Document predictions before outcomes are known.

---

### Planning Fallacy

**Definition**: Underestimating time, costs, and risks of future actions.

**In Decisions**: Overly optimistic timelines and resource estimates.

**Counter**: Use reference class forecasting; multiply estimates by 1.5-2x.

---

### Status Quo Bias

**Definition**: Preference for the current state of affairs.

**In Decisions**: Inaction feels safer even when action is better.

**Counter**: Evaluate "do nothing" as actively as "do something."

---

### Survivorship Bias

**Definition**: Focusing on winners; ignoring failures.

**In Decisions**: Learning only from success stories; underestimating failure rates.

**Counter**: Actively seek information about failures.

---

## Using This Encyclopedia

1. **Before deciding**: Scan list for biases you might be experiencing
2. **When uncertain**: Check counter-questions for your suspected biases
3. **After deciding**: Review for biases that might have influenced you
4. **In groups**: Use as discussion prompt to surface diverse perspectives

---

## Quick Reference Card

| Bias | One-Line Description | Quick Counter |
|------|---------------------|---------------|
| FOMO | Fear others are succeeding without you | Will similar opportunities exist later? |
| Sunk Cost | Continuing because of past investment | Would I start this today from scratch? |
| Authority | Trusting credentials over evidence | Does their expertise apply here? |
| Social Proof | Following the crowd | Would I do this alone? |
| Commitment | Sticking to past statements | Has new info emerged? |
| Optimism | Assuming problems will resolve | What's the base rate of failure? |
| Recency | Overweighting recent events | What does the full history show? |
| Confirmation | Seeking validating info | What would change my mind? |
| Shiny Object | Attracted to novelty | Is this better or just newer? |
| Loss Aversion | Overweighting potential losses | Am I equally weighing gains? |

```

### references/framework-deep-dives.md

```markdown
# Decision Frameworks: Deep Dives

Extended explanations and applications for each framework in the decision toolkit.

---

## First Principles Thinking

### Origin
Aristotle defined first principles as "the first basis from which a thing is known." Elon Musk popularized its modern application: breaking problems down to fundamental truths and reasoning up from there.

### The Five Questions

1. **What problem does this solve?**
   - Not "what does it do" but "what pain does it eliminate"
   - If you can't articulate the problem, the solution may be searching for one

2. **Can I solve it myself?**
   - With current skills, tools, or reasonable investment
   - Not "can someone solve it" but "can I"

3. **Is this the best solution?**
   - Compare to alternatives, including doing nothing
   - "Best" includes fit for your context, not just theoretical optimality

4. **What assumptions am I making?**
   - About the problem, the solution, the context
   - Assumptions are where first principles analysis adds most value

5. **If starting fresh today, would I choose this?**
   - The "clean slate" test
   - Removes sunk cost and path dependency

### Application Example

*Decision: Join a startup accelerator*

1. **Problem**: Need funding, network, and credibility to grow
2. **Solve myself?**: Can network independently (slower). Can't easily replicate funding access
3. **Best solution?**: Other accelerators? Angel investors? Bootstrapping?
4. **Assumptions**: Accelerator will actually provide value. Equity cost is worth it. My startup fits their focus.
5. **Fresh start?**: If I hadn't applied yet, would I? Yes — for network. Maybe — for funding.

### When to Use
- Evaluating opportunities with significant commitment
- When feeling pressured by external narratives
- When the "obvious" choice feels uncomfortable

---

## Opportunity Cost Calculator

### The Framework

```
Direct Cost = Hours × Rate
True Cost = Direct Cost + Best Alternative Value + Relationship/Growth Costs
```

### Components

**Direct Cost**
- Hours/week × weeks × hourly rate
- Use your actual billing rate, or time value equivalent

**Best Alternative Value**
- What would those hours produce if used differently?
- Not all alternatives — just the best one you'd actually pursue

**Relationship/Growth Costs**
- What connections might suffer from reduced attention?
- What skills won't develop because you're focused elsewhere?

### Application Example

*Decision: Take on a 10-hour/week consulting gig for 3 months*

| Component | Calculation | Value |
|-----------|-------------|-------|
| Direct time | 10h × 12 weeks | 120 hours |
| At rate | 120 × $200 | $24,000 |
| Best alternative | Could build feature worth ~$50K revenue | ~$50,000 |
| Relationship cost | Less time for key partnership | Hard to quantify |
| True opportunity cost | | $50,000+ |

**Insight**: The $24K consulting gig actually costs ~$50K in forgone product development.

### Common Mistakes

1. **Ignoring alternatives**: Focusing only on time, not what that time could create
2. **Undervaluing rest**: Recovery time has value; burnout has cost
3. **Ignoring compounding**: Small weekly investments compound; opportunity cost does too
4. **Only counting money**: Relationships, learning, and energy have value

---

## Scenario Matrix

### Structure

| Scenario | Probability | Outcome | Impact | Expected Value |
|----------|-------------|---------|--------|----------------|
| Worst | X% | Description | -$Y or equivalent | Prob × Impact |
| Bad | X% | | | |
| Neutral | X% | | | |
| Good | X% | | | |
| Best | X% | | | |
| **Total** | 100% | | | Sum |

### Probability Calibration

Most people are poorly calibrated. Use these anchors:

| Probability | Roughly means |
|-------------|---------------|
| 5% | "Unlikely but possible" |
| 20% | "Could happen" |
| 50% | "Coin flip" |
| 80% | "Probably" |
| 95% | "Almost certain" |

**Technique**: If you can't assign a probability, estimate "what odds would I accept if betting on this?"

### Application Example

*Decision: Launch product in January vs April*

| Scenario | Prob | January Launch | April Launch |
|----------|------|----------------|--------------|
| Market shifts | 20% | -$50K (too early) | -$20K (adapted) |
| Competitor launches | 15% | +$100K (first) | -$30K (second) |
| Product ready | 30% | +$200K | +$200K |
| Product buggy | 35% | -$80K (reputation) | +$180K (polished) |

**January EV**: (0.20×-50K) + (0.15×100K) + (0.30×200K) + (0.35×-80K) = +$27K
**April EV**: (0.20×-20K) + (0.15×-30K) + (0.30×200K) + (0.35×180K) = +$114.5K

**Insight**: April launch has higher expected value despite missing first-mover scenario.

---

## Pre-Mortem Analysis

### Origin
Gary Klein developed the pre-mortem in 1989. Unlike post-mortems (analyzing what went wrong after failure), pre-mortems imagine failure *before* it happens.

### The Process

1. **Assume failure**: "It's [future date]. This decision completely failed."
2. **Generate causes**: Brainstorm every possible reason for failure
3. **Categorize**: Which causes are within/outside your control?
4. **Identify signals**: What warning signs would precede each cause?
5. **Create triggers**: What will you do if you see those signals?

### Application Example

*Decision: Hire a new senior engineer*

**Imagine**: It's 6 months later. This hire was a disaster.

**Possible causes**:
1. Culture mismatch — brilliant but toxic to team
2. Skill mismatch — impressive resume, wrong tech stack
3. Motivation mismatch — wanted different type of work
4. Timing — we couldn't provide promised projects
5. Onboarding failure — we didn't set them up for success
6. External — they got a better offer and left

**Within control**: 1, 2, 3, 5 (interview better, onboard better)
**Outside control**: 4, 6 (market conditions)

**Warning signals**:
- Team complaints in first 2 weeks (cause 1)
- Struggles with core tasks (cause 2)
- Asks about different projects repeatedly (cause 3)

**Triggers**:
- Weekly 1:1s for first month focusing on fit
- 30/60/90 day technical assessments
- Explicit "are you getting what you expected" conversations

---

## 10-10-10 Framework

### Origin
Suzy Welch developed this framework to overcome short-term emotional reactions in decision-making.

### The Three Windows

**10 Minutes**: How will I feel immediately after deciding?
- Captures emotional reaction
- Often dominated by fear, excitement, or relief

**10 Months**: How will I feel after living with this decision?
- Captures medium-term consequences
- Initial emotions usually faded
- Actual outcomes starting to materialize

**10 Years**: How will I feel looking back on this decision?
- Captures long-term significance
- Most decisions barely remembered
- Regret patterns become clear

### Application Example

*Decision: Accept job offer at 20% pay cut for better work-life balance*

| Window | Likely Feeling | What it tells us |
|--------|----------------|------------------|
| 10 min | Anxious about money | Normal loss aversion |
| 10 months | Grateful for evenings | Lifestyle has changed |
| 10 years | Barely remember the salary | Money was fungible; time wasn't |

**Insight**: The 10-year view reveals this is primarily a lifestyle decision, not a financial one.

### When to Use
- Emotional decisions (relationship changes, big purchases)
- When short-term pain might mask long-term gain
- When caught in analysis paralysis

---

## Regret Minimization

### Origin
Jeff Bezos used this framework to decide whether to leave his finance job to start Amazon.

### The Mental Exercise

1. Imagine yourself at 80 years old
2. Looking back at your life
3. Ask: "Will I regret doing this?" and "Will I regret NOT doing this?"

### The Asymmetry of Regret

Research shows people regret things they *didn't* do more than things they did:
- Actions: Initial regret fades as we rationalize, learn, or adapt
- Inactions: Regret compounds as we wonder "what if"

### Application Example

*Decision: Leave stable corporate job to start a company*

**At 80, will I regret starting the company?**
- If it fails: "I tried. I learned. I'll never wonder."
- If it succeeds: "Life-defining achievement."

**At 80, will I regret NOT starting?**
- "I always wondered what could have been."
- "I played it safe and got the safe outcome."

**Insight**: For this type of decision, the regret of inaction typically exceeds the regret of failed action.

### Limitations
- Doesn't apply to genuinely irreversible or catastrophic decisions
- Can romanticize risk-taking; consider actual stakes
- Should complement, not replace, rational analysis

---

## Weighted Decision Matrix

### Structure

| Criterion | Weight (1-10) | Option A | Option B | Option C |
|-----------|---------------|----------|----------|----------|
| Factor 1 | 8 | Score 1-10 | Score 1-10 | Score 1-10 |
| Factor 2 | 6 | | | |
| Factor 3 | 9 | | | |
| **Weighted Total** | | Σ(weight×score) | | |

### Process

1. **List criteria**: All factors that matter for this decision
2. **Weight criteria**: How important is each? (1=low, 10=critical)
3. **Score options**: How well does each option perform? (1=poor, 10=excellent)
4. **Calculate**: Multiply weights × scores, sum totals
5. **Sanity check**: Does the winner feel right? If not, examine why.

### Application Example

*Decision: Choose between three job offers*

| Criterion | Weight | Company A | Company B | Company C |
|-----------|--------|-----------|-----------|-----------|
| Compensation | 8 | 9 | 6 | 8 |
| Growth opportunity | 9 | 5 | 9 | 7 |
| Work-life balance | 7 | 4 | 7 | 8 |
| Team quality | 8 | 8 | 7 | 6 |
| Mission alignment | 6 | 3 | 8 | 5 |
| **Weighted Total** | | 225 | 281 | 262 |

**Winner**: Company B (despite lower compensation)

### Caveats
- Weights reveal your values — examine them
- Gut disagreement with result is data (what did you miss?)
- Don't over-engineer; 5-7 criteria usually sufficient

---

## Integration: When to Use What

| Framework | Best For | Key Question |
|-----------|----------|--------------|
| First Principles | Evaluating opportunities | Can I solve this myself? |
| Opportunity Cost | Resource allocation | What am I giving up? |
| Scenario Matrix | Risk assessment | What could happen? |
| Pre-Mortem | Risk mitigation | How could this fail? |
| 10-10-10 | Emotional decisions | How will I feel later? |
| Regret Minimization | Life decisions | What will 80-year-old me think? |
| Weighted Matrix | Comparing options | Which scores highest? |

### Combining Frameworks

For major decisions, use multiple frameworks:

1. **First Principles**: Is this worth considering at all?
2. **Opportunity Cost**: Can I afford it?
3. **Scenario Matrix**: What are the likely outcomes?
4. **Pre-Mortem**: How do I mitigate risks?
5. **10-10-10 / Regret**: Does it align with my values?
6. **Final check**: Does the conclusion feel right?

```