Ebook Analysis

Ebook Analysis: Non-Fiction Knowledge Extraction

You analyze ebooks to extract knowledge with full citation traceability. This skill supports two complementary extraction modes:

1. Concept Extraction - Extract ideas classified by abstraction (principle → tactic) 2. Entity Extraction - Extract named things (studies, researchers, frameworks, anecdotes) that persist across books

Core Principle

Every extraction must be traceable to its exact source. Citation traceability is non-negotiable. Extract less with full provenance rather than more without it.

---

Two Extraction Modes

Mode 1: Concept Extraction

For extracting IDEAS organized by abstraction level.

Use when: Analyzing a book for transferable ideas, building a concept taxonomy, understanding how abstract principles relate to concrete tactics.

Output: JSON files (analysis.json, concepts.json)

Example: "Spaced repetition improves retention" is a MECHANISM at Layer 2.

Mode 2: Entity Extraction

For extracting NAMED THINGS that can be cross-referenced across books.

Use when: Building a knowledge base where the same study, researcher, or framework appears in multiple books. The goal is entity resolution—recognizing that "Hogarth's framework" in Range is the same as "kind/wicked environments" mentioned elsewhere.

Output: Markdown files in knowledge base structure

Example: "Kind vs Wicked Environments" is a FRAMEWORK by Robin Hogarth.

Choosing a Mode

---

Entity Extraction Mode (Detailed)

Entity Types

Extended Entity Type Guidance

Some entities don't fit cleanly into the five types. Guidelines:

When uncertain: Default to anecdote for narratives/events, concept for ideas, framework for systematic methods.

Author-as-Subject Pattern

When the book's author is also a significant entity (e.g., Jane McGonigal in Imaginable):

Create a researcher entity if:

• Author has notable prior work or institutional affiliation
• Author appears in Wikipedia or other reference sources
• Author's background/credentials are relevant to understanding the book
• Other books in your collection might reference them

Skip if:

• Author is primarily known only for this book
• No external sources to verify/enrich the entity

Template addition for author-subjects:

## Note
This researcher is the author of [Book] in our collection. Their frameworks and concepts are documented separately.

Entity File Template

# [Entity Name]
**Type:** study | researcher | framework | anecdote | concept
**Status:** stub | partial | solid | authoritative
**Last Updated:** YYYY-MM-DD
**Aliases:** alias1, alias2, alias3

## Summary
[2-3 sentence synthesized understanding]

## Key Findings / What It Illustrates
1. [Claim or finding with source]
   — Source: [Book], Ch.[X]

2. [Another claim]
   — Source: [Book], Ch.[X]

## Key Quotes
> "Quotable text here."

> "Another memorable quote."

## Sources in Collection
| Book | Author | How It's Used | Citation |
|------|--------|---------------|----------|
| Range | Epstein | [Role in book] | Ch.X |

## Sources NOT in Collection
- [Book that would enrich this entity]

## Related Entities
- [Other Entity](../type/other-entity.md) - Relationship description

## Open Questions
- [What we don't yet know]

Knowledge Base Structure

/knowledge/
├── _index.md                    # Master registry
├── _entities.json               # Searchable index (generated)
│
├── nonfiction/
│   ├── _index.md                # Domain index
│   ├── _[book]-quotes.md        # Book-specific quotes file
│   ├── studies/
│   │   ├── flynn-effect.md
│   │   └── chase-simon-chunking.md
│   ├── researchers/
│   │   ├── hogarth-robin.md
│   │   └── tetlock-philip.md
│   ├── frameworks/
│   │   ├── kind-vs-wicked-environments.md
│   │   └── desirable-difficulties.md
│   ├── anecdotes/
│   │   ├── tiger-vs-roger.md
│   │   └── challenger-disaster.md
│   └── concepts/
│       ├── cognitive-entrenchment.md
│       └── match-quality.md
│
├── cooking/                     # Domain-specific structure
│   ├── techniques/
│   ├── ingredients/
│   └── equipment/
│
└── technical/
    ├── patterns/
    └── technologies/

Quotes Extraction

Quotable quotes are a distinct extraction type. For each book, create a quotes file:

File: _[book-slug]-quotes.md

Structure:

# Quotable Quotes from [Book Title]
**Author:** [Author]
**Last Updated:** YYYY-MM-DD

## On [Theme 1]
> "Quote text here."

> "Another quote on same theme."

## On [Theme 2]
> "Quote on different theme."

What makes a good quote:

• Memorable phrasing that captures a key insight
• Self-contained (understandable without context)
• Surprising or counterintuitive formulation
• Useful for presentations, writing, or reference

Entity Extraction Workflow

1. Scan book - Read through identifying named studies, researchers, frameworks, illustrative stories 2. Check existing entities - Use kb-resolve-entity.ts to see if entity already exists 3. Create or update - New entity → create file; existing → add as source 4. Add quotes - Extract memorable quotes to quotes file 5. Cross-link - Add Related Entities sections 6. Regenerate index - Run kb-generate-index.ts

Entity Extraction States (KB0-KB5)

Cross-Book Synthesis Workflow

Triggered when: 2+ books have been extracted to the knowledge base.

Goals: 1. Find entities that appear in multiple books 2. Identify conceptual connections between books 3. Surface contradictions or complementary perspectives 4. Update entity files with multi-source synthesis

Process:

1. Entity overlap detection

   # Find entities with 2+ sources
   grep -l "Sources in Collection" knowledge/nonfiction/**/*.md | \
     xargs grep -l "| .* | .* |" | head -20

Or manually review entities updated with new source.

2. Conceptual connection mapping

• Compare frameworks across books (e.g., Range's "wicked environments" ↔ Imaginable's "futures thinking")
• Identify shared researchers (e.g., Tetlock appears in both Range and Imaginable)
• Look for complementary themes (prediction failure → preparation despite uncertainty)

3. Synthesis documentation For entities appearing in 2+ books, update the Summary section:

   ## Summary
   [Synthesized understanding from BOTH sources, noting agreements and differences]

4. Cross-book insights Document thematic connections in context/insights/cross-book-{theme}.md:

   # Cross-Book Insight: [Theme]

   ## Books Contributing
   - Range (Epstein) - [perspective]
   - Imaginable (McGonigal) - [perspective]

   ## Synthesis
   [How the books complement or contradict each other]

---

Concept Extraction Mode (Detailed)

Concept Types (Abstract → Concrete)

Abstraction Layers

Relationship Types

Concept Extraction States (EA0-EA7)

Concept Extraction Workflow

1. Parse - Run ea-parse.ts to chunk book with position tracking 2. Extract - Present chunks to LLM for concept identification with exact quotes 3. Classify - Assign type (principle→tactic) and layer (0-4) 4. Annotate - Add themes and functional analysis 5. Link - Connect related concepts 6. Export - Generate analysis.json, concepts.json, report.md

---

Available Tools

Parsing Tools

ea-parse.ts

Parse ebook files into chunks with metadata and position tracking.

deno run --allow-read scripts/ea-parse.ts path/to/book.txt
deno run --allow-read scripts/ea-parse.ts path/to/book.epub --format epub
deno run --allow-read scripts/ea-parse.ts book.txt --chunk-size 1500 --overlap 150

Output: JSON with metadata, chapters (if detected), and chunks with positions.

Knowledge Base Tools

kb-generate-index.ts

Scan knowledge base and generate searchable entity index.

deno run --allow-read --allow-write scripts/kb-generate-index.ts /path/to/knowledge

Output: Creates _entities.json with all entities, aliases, and metadata.

kb-resolve-entity.ts

Search for existing entities before creating duplicates.

deno run --allow-read scripts/kb-resolve-entity.ts "Flynn Effect"
deno run --allow-read scripts/kb-resolve-entity.ts "Hogarth" --threshold 0.5
deno run --allow-read scripts/kb-resolve-entity.ts "kind learning" --json

Options:

• --threshold <0-1> - Minimum match score (default: 0.3)
• --limit <n> - Maximum results (default: 5)
• --json - Output as JSON

Validation Tools

ea-validate.ts

Validate analysis output for citation accuracy and schema completeness.

deno run --allow-read scripts/ea-validate.ts analysis.json --report

---

Anti-Patterns

The Extraction Flood

Pattern: Extracting every potentially interesting phrase. Fix: Ask "Would I cite this?" before extracting. Quality over quantity.

The Citation Black Hole

Pattern: Extracting without preserving exact quotes or positions. Fix: Always capture: exact quote, chapter reference, context.

The Duplicate Entity

Pattern: Creating new entity without checking if it exists. Fix: Always run kb-resolve-entity.ts first.

The Orphan Entity

Pattern: Entities without Related Entities links. Fix: Every entity should connect to at least 2 others.

The Quote-Free Entity

Pattern: Entity captures ideas but no memorable phrasing. Fix: Include Key Quotes section with author's exact words.

The Single-Book Silo

Pattern: Analyzing books without cross-referencing. Fix: After 2+ books, run synthesis to find connections.

---

Example Workflows

Full Entity Extraction (Range Example)

1. Scan book chapter by chapter
2. Identify all named studies, researchers, frameworks, anecdotes
3. Create inventory document listing all potential entities
4. For each entity:
   a. kb-resolve-entity.ts "[entity name]" to check existence
   b. Create markdown file in appropriate type directory
   c. Fill in template with findings and citations
   d. Add Key Quotes section
5. Create _range-quotes.md with all memorable quotes
6. Update _index.md with new entities
7. kb-generate-index.ts to rebuild _entities.json

Quick Concept Scan

1. ea-parse.ts book.txt --chunk-size 2000
2. For each chunk, extract top 3-5 concepts
3. Classify by type and layer
4. Generate concepts.json and report.md

---

Output Persistence

Entity Extraction Output

Concept Extraction Output

---

Verification (Oracle)

What This Skill Can Verify

• Citation positions exist - Validate quoted text appears at claimed position
• Schema completeness - Required fields present
• Cross-reference integrity - Referenced entities exist
• Duplicate detection - Entity doesn't already exist (via kb-resolve-entity.ts)

What Requires Human Judgment

• Significance - Is this worth extracting?
• Classification - Is this really a "framework" vs "concept"?
• Relationship validity - Does A really influence B?
• Quote quality - Is this actually memorable?

---

Integration Graph

Inbound (From Other Skills)

Outbound (To Other Skills)

Complementary Skills

---

Calibration Data (from Range + Imaginable extractions)

By Book Density

By Book Subtype

Different non-fiction subtypes yield different entity profiles:

Research synthesis books cite many studies and researchers, connecting ideas across domains. Methodological books teach techniques and frameworks but cite fewer external sources. Memoir/narrative books use personal stories to illustrate points rather than research.

Metadata Reliability Warning

Book classification metadata (Calibre tags, library categories) is often:

• Wrong - Fiction/non-fiction misclassified
• Generic - "General Fiction" or "Self-Help" applied broadly
• Inconsistent - Same book categorized differently across sources

Always verify classification makes sense before extraction. A "fiction" tag on a methodology book like Imaginable is a metadata error.

---

Reasoning Requirements

Standard Reasoning

• Single chunk concept extraction
• Type/layer classification
• Simple relationship identification
• Individual entity creation

Extended Reasoning (ultrathink)

Use extended thinking for:

• Multi-book synthesis - requires holding multiple networks simultaneously
• Contradiction detection - semantic comparison across sources
• Theme emergence - identifying patterns across large sets
• Knowledge gap identification - reasoning about what's missing

Trigger phrases: "synthesize across books", "find contradictions", "identify gaps", "comprehensive analysis"

---

What You Do NOT Do

• Extract without citation traceability
• Create entities without checking for duplicates
• Skip the linking phase (orphan entities are not useful)
• Leave entities without quotes
• Treat fiction as non-fiction
• Use regex for semantic analysis (LLM judgment only)

Abstraction Layers (0-4)

This reference defines the five abstraction layers used to classify concepts from most abstract (Layer 0) to most concrete (Layer 4). Use these definitions to guide classification.

Overview

---

Layer 0: Foundational

Definition: Universal principles that apply across domains and cultures. These are the bedrock truths about human nature, systems, or reality.

Characteristics:

• Domain-agnostic (applies everywhere)
• Timeless (true across eras)
• About fundamental nature
• Few in number per domain

Questions to Identify Layer 0:

• Would this be true in any culture or time period?
• Does this apply beyond the specific domain discussed?
• Is this about human nature or universal systems?

Examples:

• "Humans form groups for survival advantage"
• "Complex systems resist change"
• "Scarcity increases perceived value"
• "Trust enables cooperation"

Not Layer 0:

• Anything that requires specific context
• Concepts tied to modern technology or practices
• Domain-specific frameworks

---

Layer 1: Theoretical

Definition: Domain-specific theory that explains how the foundational principles manifest in a particular field. These are the "laws" of the domain.

Characteristics:

• Specific to a domain (communities, learning, leadership, etc.)
• Explanatory (tells why things work in this domain)
• Forms basis for strategies
• Multiple theories may exist

Questions to Identify Layer 1:

• Is this specific to one domain but general within it?
• Does this explain how foundational principles apply here?
• Would experts in this field recognize this as theoretical foundation?

Examples (Community Building):

• "Communities form around shared identity"
• "Engagement follows the commitment-consistency principle"
• "Network effects drive community value"

Examples (Learning):

• "Memory consolidates during sleep"
• "Active recall strengthens retention"
• "Spacing improves long-term learning"

Not Layer 1:

• Universal truths (those are Layer 0)
• Specific practices or methods (those are Layer 3-4)
• Frameworks with multiple components (those are often Layer 2)

---

Layer 2: Strategic

Definition: Approaches, frameworks, and models that translate theory into actionable direction. These provide structure for how to think about problems in the domain.

Characteristics:

• Has named components or phases
• Provides decision-making guidance
• Can be implemented multiple ways
• Often visualizable (diagrams, matrices)

Questions to Identify Layer 2:

• Is this a framework or model?
• Does it have multiple components or stages?
• Does it guide how to approach problems?

Examples (Community Building):

• "The community lifecycle: formation, growth, maturation, renewal"
• "The engagement ladder: lurker → participant → contributor → leader"
• "The three pillars of community: connection, content, collaboration"

Examples (Product Development):

• "Build-Measure-Learn cycle"
• "The MVP approach"
• "Jobs to be done framework"

Not Layer 2:

• Single techniques (those are Layer 3)
• Theoretical explanations (those are Layer 1)
• Tool recommendations (those are Layer 4)

---

Layer 3: Tactical

Definition: Specific methods, techniques, and practices that implement strategies. These are concrete enough to be directly actionable but not tied to specific tools.

Characteristics:

• Directly actionable
• Can be done without specific tools
• Has clear success criteria
• Reusable across contexts

Questions to Identify Layer 3:

• Can someone implement this directly?
• Is it independent of specific tools?
• Would this work with various implementations?

Examples (Community Building):

• "Create onboarding sequences for new members"
• "Host regular events at consistent times"
• "Recognize contributions publicly"
• "Pair new members with experienced mentors"

Examples (Writing):

• "Outline before drafting"
• "Read your work aloud for rhythm"
• "Start with the end in mind"

Not Layer 3:

• Tool-specific instructions (those are Layer 4)
• High-level approaches (those are Layer 2)
• Explanations without actions (those are Layer 1)

---

Layer 4: Specific

Definition: Concrete implementations tied to specific tools, platforms, time periods, or contexts. These are the most actionable but also the most likely to become outdated.

Characteristics:

• Names specific tools, platforms, or products
• May include specific numbers or thresholds
• Time-bound or context-bound
• Most perishable layer

Questions to Identify Layer 4:

• Does this name a specific tool or platform?
• Would this become outdated if technology changes?
• Is this tied to a particular time, place, or organization?

Examples (Community Building):

• "Use Discourse for forums"
• "Set up a #introductions channel in Slack"
• "Send the welcome email at 9am local time"
• "Aim for 30% response rate in the first week"

Examples (Software Development):

• "Use React for the frontend"
• "Deploy to AWS Lambda"
• "Set MAX_CONNECTIONS to 100"

Not Layer 4:

• Generic techniques without tool names (those are Layer 3)
• Frameworks or models (those are Layer 2)

---

Layer Assignment Guidelines

Default to Higher Layers

When uncertain, assign to the higher (more abstract) layer. Reasons:

• Abstract concepts are more reusable
• They're more likely to remain valid over time
• Specifics can always be derived from abstractions

Consider the Author's Intent

The same phrase can exist at different layers depending on context:

• "Use events to build community" (Layer 3 - tactic)
• "Events create shared experiences that reinforce identity" (Layer 1 - theory)
• "Host a monthly Zoom meetup on the first Thursday" (Layer 4 - specific)

Track Layer Distribution

A well-extracted book should have concepts across multiple layers:

• Few Layer 0 concepts (2-5 typically)
• More Layer 1-2 concepts (the book's theoretical contribution)
• Many Layer 3-4 concepts (practical advice)

If extraction is heavily weighted to one layer, review for missed concepts at other layers.

---

Cross-Reference with Concept Types

Certain concept types cluster at certain layers:

This is guidance, not rule. A Layer 0 mechanism exists ("Reciprocity operates through obligation"), as does a Layer 4 pattern ("The onboarding flow: welcome email → profile setup → first action").

---

When Layer is Unclear

1. Look at surrounding context for abstraction level 2. Consider how reusable/portable the concept is 3. Note uncertainty in the concept record 4. Prefer higher layers when genuinely ambiguous 5. Flag for human review if the distinction matters for synthesis

Concept Types

This reference defines the five concept types used in ebook analysis. Use these definitions to guide classification - they are guidance for judgment, not rigid rules.

The Five Types

Principle

Definition: A foundational truth, axiom, or universal claim about how things work.

Distinguishing Features:

• Asserts something IS true (not how to do something)
• Often stated as timeless or universal
• Serves as foundation for other concepts
• Usually abstract and broadly applicable

Language Signals:

• "X is essential for Y"
• "The fundamental truth is..."
• "At its core, X requires Y"
• Declarative statements about nature of things

Examples:

• "Communities form around shared identity" (community building)
• "Trust is earned through consistent action" (leadership)
• "Complex systems exhibit emergent behavior" (systems thinking)

Not Principles:

• Step-by-step processes (those are tactics)
• Frameworks with multiple components (those are patterns)
• Recommendations for action (those are strategies)

---

Mechanism

Definition: An explanation of HOW something works - the causal chain or process by which effects occur.

Distinguishing Features:

• Explains causation (A leads to B because...)
• Describes internal workings
• Can be observed or tested
• Shows the "gears" behind outcomes

Language Signals:

• "X works by..."
• "The way this happens is..."
• "When A occurs, B follows because..."
• "The underlying process involves..."

Examples:

• "Reciprocity creates social bonds by triggering obligation responses" (social dynamics)
• "Spaced repetition enhances memory by strengthening neural pathways during recall" (learning)
• "Network effects increase value as more users join because each new connection adds multiple potential relationships" (technology)

Not Mechanisms:

• Simple observations without explanation (those may be principles)
• How-to instructions (those are tactics)
• Descriptions of what something is (those may be patterns)

---

Pattern

Definition: A recurring structure, framework, or recognizable arrangement that appears across multiple instances.

Distinguishing Features:

• Describes a shape or structure
• Can be observed in multiple contexts
• Has named components or phases
• Provides a mental model or framework

Language Signals:

• "The X pattern involves..."
• "This follows a common structure of..."
• "The framework consists of..."
• "There are N stages/phases/components..."

Examples:

• "The hero's journey pattern: departure, initiation, return" (storytelling)
• "The community lifecycle: founding, growth, maturation, renewal" (communities)
• "The five stages of grief: denial, anger, bargaining, depression, acceptance" (psychology)

Not Patterns:

• Single actions or techniques (those are tactics)
• Explanations of why things work (those are mechanisms)
• Recommendations without structure (those are strategies)

---

Strategy

Definition: A high-level approach or orientation for achieving goals - the "how to think about" rather than "how to do."

Distinguishing Features:

• Provides direction without specifying exact steps
• Can be implemented in multiple ways
• Involves trade-offs and priorities
• Guides decision-making

Language Signals:

• "The approach should be..."
• "Focus on X before Y"
• "Prioritize..."
• "The key is to..."
• "Rather than X, consider Y"

Examples:

• "Build trust before asking for contribution" (community building)
• "Fail fast and iterate" (product development)
• "Invest in relationships during good times" (leadership)

Not Strategies:

• Specific techniques (those are tactics)
• Frameworks with defined components (those are patterns)
• Explanations of why things work (those are mechanisms)

---

Tactic

Definition: A specific, actionable technique or practice that can be directly implemented.

Distinguishing Features:

• Concrete and specific
• Can be done immediately
• Has clear success criteria
• Often includes tools, templates, or scripts

Language Signals:

• "Do X"
• "Send/Create/Write/Build..."
• "Use the following template..."
• "Every day, do..."
• Imperative verbs

Examples:

• "Send welcome emails within 24 hours of signup" (community building)
• "Use the STAR format for behavioral interviews" (hiring)
• "Write three things you're grateful for each morning" (wellbeing)

Not Tactics:

• General approaches (those are strategies)
• Explanations of why (those are mechanisms)
• Broad truths (those are principles)

---

Classification Decision Tree

When classifying a concept, ask:

1. Is it an actionable instruction?

• Yes → Probably TACTIC
• No → Continue

2. Does it explain HOW something causes an effect?

• Yes → Probably MECHANISM
• No → Continue

3. Does it describe a recurring structure or framework?

• Yes → Probably PATTERN
• No → Continue

4. Does it provide high-level guidance for achieving goals?

• Yes → Probably STRATEGY
• No → Continue

5. Does it assert a foundational truth about how things work?

• Yes → Probably PRINCIPLE
• No → Review - may need more context or may be too vague to extract

---

Boundary Cases

Principle vs Mechanism

• Principle: "Trust is essential for collaboration"
• Mechanism: "Trust enables collaboration by reducing transaction costs"
• The mechanism explains WHY the principle is true

Mechanism vs Pattern

• Mechanism: "Feedback loops amplify small changes"
• Pattern: "The growth-plateau-renewal cycle"
• Patterns describe structure; mechanisms explain causation

Strategy vs Tactic

• Strategy: "Prioritize quality over quantity"
• Tactic: "Review each post before publishing using this checklist"
• If you can do it in one sitting, it's probably a tactic

Pattern vs Principle

• Pattern: "The five stages of team development"
• Principle: "Teams require psychological safety to perform"
• Patterns have structure; principles are singular claims

---

When Classification is Unclear

If a concept doesn't clearly fit one type:

1. Consider the author's apparent intent 2. Look at surrounding context for clues 3. Choose the type that best serves retrieval 4. Note uncertainty in the concept record 5. Flag for human review if needed

It's better to classify with noted uncertainty than to skip extraction of a valuable concept.

Functional Axes for Non-Fiction Analysis

This reference adapts the six-axis functional analysis framework (from dna-extraction) for non-fiction concept analysis. Use these axes to understand not just WHAT a concept says, but what it DOES.

Core Principle

The value of a concept is in its function, not just its content.

A concept like "trust enables collaboration" isn't just a statement to record - it serves multiple functions in the book's argument, the reader's understanding, and the broader knowledge domain.

The Six Axes (Adapted for Non-Fiction)

---

Axis 1: Form

Question: How is this concept presented?

The surface articulation - the specific words, examples, and framing the author uses. This is what we directly extract and cite.

What to Capture:

• Exact phrasing used
• Examples given
• Analogies or metaphors
• Visual representations (if any)
• The author's specific terminology

Why It Matters:

• Preserves the author's voice
• Enables accurate citation
• May reveal author's perspective or bias
• Different forms suit different audiences

Example:

• Form: "Trust is the glue that holds communities together"
• Note: Metaphor-based presentation; emphasizes cohesion function

Form vs. Function: The form is "glue metaphor." The function is "explains why trust matters for community cohesion."

---

Axis 2: Structural Function

Question: How does this concept support the book's argument?

The role this concept plays in the book's overall logical structure. Is it a premise? A conclusion? Evidence? A transition?

Structural Roles:

• Foundation: Premises the argument rests on
• Pillar: Major supporting points
• Evidence: Data or examples backing claims
• Synthesis: Conclusions drawn from earlier points
• Bridge: Transitions between major sections
• Counterpoint: Anticipated objections and responses

What to Capture:

• Where this concept appears in the book's structure
• What it supports or enables
• What depends on it
• How it connects to the thesis

Example:

• Concept: "Communities form around shared identity"
• Structural Function: Foundation - this is a premise that subsequent chapters build on

Why It Matters:

• Helps understand what's load-bearing vs. decorative
• Enables reconstruction of the book's argument
• Shows what would break if this concept were removed

---

Axis 3: Application Function

Question: How can this concept be used by the reader?

The practical utility - what actions, decisions, or understanding this enables.

Application Types:

• Diagnostic: Helps identify problems or states
• Prescriptive: Guides specific actions
• Evaluative: Provides criteria for judgment
• Predictive: Enables forecasting outcomes
• Explanatory: Helps understand phenomena
• Generative: Enables creation of new things

What to Capture:

• What someone could DO with this knowledge
• What decisions it informs
• What problems it helps solve
• What capabilities it enables

Example:

• Concept: "Communities need shared rituals"
• Application Function: Prescriptive (guides action) + Diagnostic (explains why some communities fail)

Why It Matters:

• Determines the concept's practical value
• Helps readers apply knowledge
• Identifies actionable vs. theoretical concepts

---

Axis 4: Emotional Function

Question: What response does this concept create in readers?

The motivational or affective dimension - how this concept makes readers feel and why that matters.

Emotional Functions:

• Validates: Confirms reader's existing beliefs/experiences
• Challenges: Disrupts assumptions, creates productive discomfort
• Inspires: Motivates action or aspiration
• Reassures: Reduces anxiety about complexity
• Clarifies: Relief of understanding something confusing
• Connects: Creates sense of shared understanding

What to Capture:

• What emotional state the author seems to want to create
• How examples and framing contribute to emotional response
• Whether the concept is meant to comfort or challenge

Example:

• Concept: "Most community-building advice is backwards"
• Emotional Function: Challenges (disrupts), then Clarifies (the correction provides relief)

Why It Matters:

• Emotional resonance affects retention and application
• Helps understand why certain concepts "stick"
• Reveals author's rhetorical strategy

---

Axis 5: Thematic Function

Question: What broader ideas does this concept connect to?

The intellectual context - how this concept fits into larger conversations, fields, and themes.

Thematic Connections:

• Field placement: Where does this fit in the discipline?
• Historical context: What intellectual tradition is this part of?
• Adjacent themes: What other big ideas does this relate to?
• Debates: What ongoing conversations does this engage?
• Paradigms: What worldview does this assume or challenge?

What to Capture:

• What larger themes this concept exemplifies
• What intellectual traditions it draws from
• How it relates to debates in the field
• What assumptions it makes about the world

Example:

• Concept: "Community membership is performative, not given"
• Thematic Function: Connects to social constructionism, performance theory, identity politics debates

Why It Matters:

• Enables cross-book synthesis
• Reveals intellectual lineage
• Helps position concept in broader knowledge

---

Axis 6: Relational Function

Question: How does this concept connect to other concepts?

The web of relationships - how concepts interact, support, contradict, or build on each other.

Relational Types:

• Prerequisite: What must be understood first?
• Enables: What other concepts does this make possible?
• Conflicts: What concepts does this tension with?
• Exemplifies: What higher-level concepts does this demonstrate?
• Decomposes: What sub-concepts does this break into?
• Parallels: What concepts in other domains are similar?

What to Capture:

• Direct relationships mentioned by author
• Implicit relationships from proximity or structure
• Cross-book relationships
• Relationships to concepts from other domains

Example:

• Concept: "Trust requires competence AND character"
• Relational Function: Decomposes into two sub-concepts; contradicts "trust is just about likability"; enables "specific trust-building tactics"

Why It Matters:

• Builds the knowledge network
• Enables navigation and discovery
• Supports synthesis across sources

---

Applying the Six Axes

When to Use Full Six-Axis Analysis

Use full analysis for:

• Key concepts central to the book's argument
• Novel or surprising concepts
• Concepts that will be used in synthesis

Use abbreviated analysis for:

• Supporting examples
• Well-established concepts
• Highly specific implementations

Six-Axis Template

For each significant concept:

**Concept:** [Name or phrase]
**Citation:** [Exact quote with position]

**Axes:**
1. Form: [How it's presented]
2. Structural: [Role in argument]
3. Application: [How it can be used]
4. Emotional: [What response it creates]
5. Thematic: [What ideas it connects to]
6. Relational: [How it connects to other concepts]

Example: Complete Six-Axis Extraction

Concept: "The community lifecycle follows a pattern of formation, growth, maturation, and renewal"

Citation: "Every community... goes through predictable stages..." (p. 45, chars 12340-12520)

Axes: 1. Form: Four-stage cyclical model, explicitly named stages, biological metaphor 2. Structural: Framework that organizes Part II of the book; each chapter addresses one stage 3. Application: Diagnostic (identify which stage you're in); Prescriptive (different tactics per stage) 4. Emotional: Reassures (stages are normal); Validates (explains past community experiences) 5. Thematic: Connects to lifecycle thinking in business, product management, organizational development 6. Relational:

• Prerequisite: "Communities exist" (basic definition)
• Enables: Stage-specific tactics (Chapters 5-8)
• Parallels: Product lifecycle, organizational development stages
• Decomposes: Four sub-concepts (formation, growth, maturation, renewal)

---

Integration with Concept Classification

The six axes complement type and layer classification:

A complete concept record includes:

• Type classification
• Layer assignment
• Full citation with position
• Six-axis functional analysis (for key concepts)
• Relationship links

---

When Six-Axis Analysis Adds Value

High Value:

• Cross-book synthesis (understanding what each concept does enables better comparison)
• Concept retrieval (functional annotations improve search)
• Application planning (knowing application function helps implementation)

Lower Value:

• Simple concept extraction (full analysis is overkill for minor points)
• High-volume extraction (time-consuming for every concept)
• Well-known concepts (don't need to analyze "trust is important")

Recommendation: Apply full six-axis analysis to ~20% of extracted concepts (the most important ones). Use abbreviated analysis for the rest.

Relationship Types

This reference defines the relationship types used to link concepts. Use these definitions to guide relationship creation.

Overview

---

INFLUENCES

Definition: Concept A has a causal or correlational effect on Concept B. A change in A would affect B.

When to Use:

• A causes B to happen
• A enables or facilitates B
• A inhibits or prevents B
• A is a precondition for B

Strength Values:

• Positive (+0.1 to +1.0): A increases/enables B
• Negative (-0.1 to -1.0): A decreases/inhibits B
• Strong (±0.7 to ±1.0): Direct causal relationship
• Moderate (±0.4 to ±0.6): Significant but indirect
• Weak (±0.1 to ±0.3): Correlational or minor

Examples:

• "Trust" INFLUENCES→ "Collaboration" (strength: +0.8)
• "Fear" INFLUENCES→ "Risk-taking" (strength: -0.7)
• "Shared identity" INFLUENCES→ "Community cohesion" (strength: +0.9)

Not INFLUENCES:

• A simply mentions B (use context, not relationship)
• A is a component of B (use COMPOSED_OF)
• A is evidence for B (use SUPPORTS)

---

SUPPORTS

Definition: Concept A provides evidence, validation, or backing for Concept B. A makes B more credible or justified.

When to Use:

• A is empirical evidence for B
• A is an example that demonstrates B
• A is a theoretical justification for B
• A is a citation or reference for B

Strength Values:

• Strong: Direct empirical evidence or proof
• Moderate: Good example or theoretical support
• Weak: Tangential or partial support

Examples:

• "Research study X" SUPPORTS→ "Spaced repetition improves retention"
• "Case study of Company Y" SUPPORTS→ "Community-led growth works"
• "Historical precedent Z" SUPPORTS→ "Revolutions follow pattern P"

Not SUPPORTS:

• A causes B to happen (use INFLUENCES)
• A is part of B (use COMPOSED_OF)
• B is derived from A (use DERIVES_FROM)

---

CONTRADICTS

Definition: Concept A conflicts with, opposes, or is incompatible with Concept B. They cannot both be true in the same context.

When to Use:

• A and B make opposite claims
• A and B recommend incompatible approaches
• Evidence for A undermines B
• A and B are mutually exclusive

Strength Values:

• Strong: Direct logical contradiction
• Moderate: Significant tension or incompatibility
• Weak: Partial tension or contextual conflict

Types of Contradiction: 1. Theoretical: Different claims about how things work 2. Practical: Different recommendations for action 3. Contextual: True in different contexts but not compatible

Examples:

• "Move fast and break things" CONTRADICTS↔ "Measure twice, cut once"
• "Communities need strong leadership" CONTRADICTS↔ "Communities should be self-organizing"
• "Research shows X" CONTRADICTS↔ "Research shows not-X"

Bidirectionality: CONTRADICTS is bidirectional - if A contradicts B, then B contradicts A.

Not CONTRADICTS:

• A is simply different from B (difference ≠ contradiction)
• A and B apply in different contexts (may just be contextual)
• A and B are different levels of abstraction

---

COMPOSED_OF

Definition: Concept A contains Concept B as a component, element, or part. B is nested within A.

When to Use:

• B is a named component of framework A
• B is a step in process A
• B is a required element of A
• A explicitly includes B in its definition

Component Types:

• Prerequisite: B must exist before A
• Component: B is a part of A
• Variant: B is a subtype of A

Examples:

• "Hero's journey" COMPOSED_OF→ "Departure"
• "Hero's journey" COMPOSED_OF→ "Initiation"
• "Hero's journey" COMPOSED_OF→ "Return"
• "Trust" COMPOSED_OF→ "Competence trust" (variant)
• "Trust" COMPOSED_OF→ "Character trust" (variant)

Not COMPOSED_OF:

• B merely relates to A (use INFLUENCES or other)
• B is evidence for A (use SUPPORTS)
• B causes A (use INFLUENCES)

---

DERIVES_FROM

Definition: Concept A is logically derived from, emerges from, or is a consequence of Concept B. A exists because of B.

When to Use:

• A is a logical conclusion from B
• A emerges from B in a system
• A is an application of B to a context
• A is a specialization of B

Derivation Types:

• Logical conclusion: A follows from B by reasoning
• Emergent property: A arises from B in complex systems
• Synthesis: A combines multiple sources including B

Examples:

• "Community guidelines" DERIVES_FROM→ "Shared values"
• "Specific onboarding tactics" DERIVES_FROM→ "Engagement theory"
• "Leadership practices" DERIVES_FROM→ "Trust principles"

Not DERIVES_FROM:

• B influences A (that's INFLUENCES)
• A is part of B (that's the reverse - B COMPOSED_OF A)
• A is evidence for B (that's the reverse - A SUPPORTS B)

---

Creating Relationships

When to Create a Relationship

Create a relationship when: 1. The connection is explicitly stated in the source 2. The connection is strongly implied by context 3. The connection would be useful for synthesis and querying

Do NOT create relationships:

• Based on mere co-occurrence in text
• When the connection is trivial or obvious
• When evidence for the connection is weak

Relationship Density

Aim for:

• Every concept linked to at least 1-2 others
• Key concepts (hubs) linked to many others
• Both within-book and cross-book relationships

Avoid:

• Orphan concepts with no relationships
• Over-connected concepts (>10 relationships may indicate over-extraction)
• Circular relationships without clear semantics

Relationship Confidence

Track confidence in relationships:

• High (0.8-1.0): Explicitly stated in source
• Medium (0.5-0.7): Strongly implied or inferred
• Low (0.2-0.4): Reasonable inference, less certain

Flag low-confidence relationships for human review.

---

Cross-Book Relationships

When analyzing multiple books, additional patterns emerge:

Agreement

Both authors say A INFLUENCES B → Stronger confidence

Complementarity

Author 1 says A INFLUENCES B Author 2 says B INFLUENCES C Combined: A → B → C pathway

Contradiction

Author 1 says A SUPPORTS claim X Author 2 says B CONTRADICTS claim X Flag for synthesis discussion

Extension

Author 1 defines framework F Author 2 applies F to new context DERIVES_FROM relationship across books

---

Relationship Examples by Domain

Community Building

• "Trust" INFLUENCES→ "Participation" (+0.8)
• "Shared identity" INFLUENCES→ "Retention" (+0.7)
• "Explicit guidelines" SUPPORTS→ "Safe participation"
• "Top-down control" CONTRADICTS↔ "Self-organization"
• "Engagement ladder" COMPOSED_OF→ "Lurker stage"

Learning

• "Active recall" INFLUENCES→ "Retention" (+0.9)
• "Spacing effect" SUPPORTS→ "Spaced repetition works"
• "Massed practice" CONTRADICTS↔ "Distributed practice"
• "Learning pyramid" COMPOSED_OF→ "Reading (10%)"
• "Retrieval practice" DERIVES_FROM→ "Testing effect research"

Leadership

• "Psychological safety" INFLUENCES→ "Team performance" (+0.8)
• "Google Project Aristotle" SUPPORTS→ "Safety matters"
• "Servant leadership" CONTRADICTS↔ "Command-and-control"
• "Situational leadership" COMPOSED_OF→ "Directing style"
• "Specific feedback tactics" DERIVES_FROM→ "Growth mindset theory"