ebook-analysis
Parse ebooks, extract concepts and entities with citation traceability, classify by type/layer, and synthesize across book collections.
npx skills add majiayu000/claude-skill-registry --skill ebook-analysis-jwynia-agent-skills --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Analyzes ebooks to extract knowledge with full citation traceability. Supports two extraction modes: Concept Extraction (ideas and abstraction layers) and Entity Extraction (named studies, researchers, frameworks, anecdotes, concepts) across books, with outputs as JSON files for concepts and analysis in a knowledge base structure.
How it works
- Mode 1: Concept Extraction focuses on ideas categorized by abstraction level (Principle, Mechanism, Pattern, Strategy, Tactic) and abstraction layers (0 to 4). Outputs include analysis.json and concepts.json.
- Mode 2: Entity Extraction identifies named entities (study, researcher, framework, anecdote, concept) and outputs Markdown files organized in a knowledge base structure. It includes an entity file template and a quotes extraction workflow.
- The extraction workflow comprises parsing ebooks with ea-parse.ts, running kb-resolve-entity.ts to check for duplicates, creating/updating entity files, adding quotes, linking related entities, and regenerating the index via kb-generate-index.ts.
- Cross-book synthesis is supported after multiple books are processed, using cross-book overlap detection and synthesis documentation.
When to use it
Use Mode 1 when you want to understand a book's argument structure or create actionable takeaways via conceptual extraction. Use Mode 2 when building a reference library across books to resolve entities and track how researchers, studies, frameworks, anecdotes, and concepts appear across sources. Both modes can be run sequentially for comprehensive coverage.
What it can touch
- Parsing tools: ea-parse.ts
- Knowledge base tools: kb-generate-index.ts, kb-resolve-entity.ts
- Validation tools: ea-validate.ts
- Outputs: analysis.json, concepts.json, and various Markdown files under a knowledge base structure for entities, quotes, and cross-book synthesis
Caveats
- Emphasizes citation traceability; extracts with provenance rather than volume without sources
- Requires checking for entity duplicates before creation
- Cross-book synthesis is triggered after 2+ books have been processed; details are provided in the workflow
# 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
- Core Principle
- Two Extraction Modes
- Mode 1: Concept Extraction
- Mode 2: Entity Extraction
- Choosing a Mode
- Entity Extraction Mode (Detailed)
- Entity Types
- Extended Entity Type Guidance
- Author-as-Subject Pattern
- Entity File Template
- Knowledge Base Structure
- Quotes Extraction
- Entity Extraction Workflow
- Entity Extraction States (KB0-KB5)
grep -l "Sources in Collection" knowledge/nonfiction/**/*.md | \ xargs grep -l "| .* | .* |" | head -20 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 deno run --allow-read --allow-write scripts/kb-generate-index.ts /path/to/knowledge 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 deno run --allow-read scripts/ea-validate.ts analysis.json --report
What does the ebook-analysis skill do?
Parse ebooks, extract concepts and entities with citation traceability, classify by type/layer, and synthesize across book collections.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ebook-analysis-jwynia-agent-skills --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.