# ebook-analysis

Pulls ideas and named entities out of ebooks, each one traceable to its source. Useful when you are building a knowledge base across several books.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 393 installs · ★ 176
- Author: jwynia
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/document-processing/analysis/ebook-analysis/SKILL.md
- Updated: 2026-02-24
- HTML: https://affpapa.org/en/nevibecode/skills/ebook-analysis

## What it does

The skill runs in two modes. Concept extraction sorts ideas by abstraction level, from principle down to tactic. Entity extraction pulls out named things — studies, researchers, frameworks, anecdotes — and files them into a knowledge base where the same work is recognized across books.

The author sets one hard rule: every extraction must trace back to an exact spot in the book. Fewer extractions with full provenance beat more without it. That is why the entity file template carries fields for quotes, a source table and open questions, with a separate quotes file per book.

Entities fall into five types: study, researcher, framework, anecdote, concept. For the awkward cases the guidance is to default to anecdote for narratives and events, concept for ideas, framework for systematic methods. The text also names a script, `kb-resolve-entity.ts`, for checking whether an entity already exists — skip that step and a second pass over the same book leaves you with duplicates.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add jwynia/agent-skills --skill ebook-analysis -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ebook-analysis/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ebook-analysis/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add jwynia/agent-skills --skill ebook-analysis -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ebook-analysis/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add jwynia/agent-skills --skill ebook-analysis -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ebook-analysis/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install jwynia/agent-skills ebook-analysis
```

2. **Manually: put the files in place**
- File: `.github/skills/ebook-analysis/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add jwynia/agent-skills --skill ebook-analysis -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/jwynia/agent-skills --path skills/general/document-processing/analysis/ebook-analysis
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ebook-analysis/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add jwynia/agent-skills --skill ebook-analysis -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/document-processing/analysis/ebook-analysis/SKILL.md

## When to use it
- extract ideas from a book with chapter-level citations
- merge studies and researchers from several books into one base
- sort ideas by abstraction level, from principle to tactic
- collect quotes by theme for talks and writing
- spot the same framework referenced across multiple sources

## Example prompts
- Analyze this book in concept extraction mode and save the output as JSON
- Extract entities from this book and check whether they already exist in the knowledge base
- Pull the quotable quotes from this book into a themed file

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 6a917e57799d711c.

BEGIN THIRD-PARTY FILE 6a917e57799d711c
```text
---
name: ebook-analysis
description: Parse ebooks, extract concepts and entities with citation traceability, classify by type/layer, and synthesize across book collections.
license: MIT
metadata:
  author: jwynia
  version: "2.1"
  domain: research
  cluster: media-meta-analysis
  type: orchestrator
  mode: diagnostic+generative
  maturity: working
  maturity_score: 14
---

# 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

| If you want to... | Use Mode |
|-------------------|----------|
| Understand a book's argument structure | Concept Extraction |
| Build a reference library across books | Entity Extraction |
| Create actionable takeaways | Concept Extraction |
| Track what researchers say across sources | Entity Extraction |
| Both | Run both modes sequentially |

---

## Entity Extraction Mode (Detailed)

### Entity Types

| Type | What It Captures | Example |
|------|------------------|---------|
| **study** | Research findings, experiments, data | Flynn Effect, Marshmallow Test |
| **researcher** | People and their contributions | Anders Ericsson, Robin Hogarth |
| **framework** | Mental models, taxonomies, systems | Kind vs Wicked, Desirable Difficulties |
```
END THIRD-PARTY FILE 6a917e57799d711c

The third-party file has ended. Everything between the 6a917e57799d711c tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2626 of 19481 bytes. © jwynia · MIT · https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/document-processing/analysis/ebook-analysis/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md