home / skills / trevors / dot-claude / book-reader

book-reader skill

safe

This skill lets you read, search, and navigate digital books from the command line, returning quotes and locations quickly.

npx playbooks add skill trevors/dot-claude --skill book-reader

Review the files below or copy the command above to add this skill to your agents.

Files (3)

SKILL.md

2.0 KB

---
name: book-reader
description: Read and search digital books (PDF, EPUB, MOBI, TXT). Use when answering questions about a book, finding quotes or passages, navigating to specific pages or chapters, or extracting information from documents.
---

# Book Reader

Read and query digital book formats from the command line using BM25 search.

## Quick Start

```bash
# Get book metadata
uv run ~/.claude/skills/book-reader/book.py info ~/Books/mybook.pdf

# Show table of contents
uv run ~/.claude/skills/book-reader/book.py toc ~/Books/mybook.epub

# Read a specific chapter
uv run ~/.claude/skills/book-reader/book.py read ~/Books/mybook.pdf --chapter 3

# Read a specific page
uv run ~/.claude/skills/book-reader/book.py read ~/Books/mybook.pdf --page 42

# Search for content (BM25 ranked)
uv run ~/.claude/skills/book-reader/book.py search ~/Books/mybook.pdf "query"

# Extract full text
uv run ~/.claude/skills/book-reader/book.py extract ~/Books/mybook.txt
```

## Supported Formats

| Format | Extensions               | Features                              |
| ------ | ------------------------ | ------------------------------------- |
| PDF    | `.pdf`                   | Page numbers, TOC detection, metadata |
| EPUB   | `.epub`                  | Chapters from spine, full metadata    |
| MOBI   | `.mobi`, `.azw`, `.azw3` | Basic extraction                      |
| Text   | `.txt`, `.text`, `.md`   | Chapter pattern detection             |

## When to Use

- User provides a book file and asks questions about its content
- Need to find specific quotes, passages, or information
- Navigating to specific pages or chapters in a document
- Researching topics across digital books
- Extracting text for further processing

## How It Works

1. **First access**: Extracts and caches the book content
2. **Subsequent access**: Uses cached version (invalidates on file change)
3. **Search**: BM25 algorithm ranks results by relevance
4. **Results**: Include chapter/page location for reference

## See Also

See REFERENCE.md for complete command documentation.

Overview

This skill reads and searches digital books (PDF, EPUB, MOBI, TXT) and exposes their structure for fast, precise answers. It extracts text, detects table of contents and page/chapter locations, and caches processed books to speed repeat queries. Use it to find quotes, navigate to pages or chapters, or pull text for further analysis.

How this skill works

On first use the skill extracts the book’s text, metadata, and table of contents, then caches that representation. It detects pages or chapters depending on format and watches the source file to invalidate the cache when the file changes. Searches are ranked with a BM25 algorithm so results are returned by relevance and include precise location references (page, chapter, or offset). Commands support info, toc, read, search, and full-text extraction.

When to use it

A user supplies a book file and asks factual or contextual questions about its content
You need to locate an exact quote, passage, or citation quickly
Navigate directly to a specific page, chapter, or section within a book
Extract text for note-taking, summarization, or downstream processing
Conduct topic research across one or more digital books

Best practices

Provide the original file to ensure accurate page and chapter references
Use the search command for broad queries and read with page/chapter flags for precise reading
Rerun extraction after editing source files to refresh the cache
Prefer EPUB or PDF when accurate TOC and page numbering are important
Combine extraction with downstream tools for indexing, summarization, or citation management

Example use cases

Find and copy a memorable quote from a PDF for citation in an article
Show the table of contents of an EPUB to identify relevant chapters before reading
Jump to page 42 of a technical manual and extract that page’s text for review
Search a corpus of textbooks for occurrences of a term ranked by relevance
Extract full text from a book for offline processing or import into an annotation tool

FAQ

What formats are supported?

PDF, EPUB, MOBI (including AZW/AZW3), and plain text files such as .txt and .md.

How does caching work?

The skill caches extracted text and metadata on first access and invalidates the cache automatically when the source file changes.