skills.rest
mintuz
mintuzCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

read-book

Extract structured notes, quotes, and study cards from books in PDF, EPUB, MOBI, and text formats.

3|Updated Nov 8, 2014
Search Tags:#summarization#pdf#pandoc#spaced repetition#second brain#epub#book notes
One-click install
npx skills add https://github.com/mintuz/.dotfiles --skill read-book-mintuz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: read-book
Source: https://github.com/mintuz/.dotfiles/tree/main/agents/.agents/skills/read-book
Command: npx skills add https://github.com/mintuz/.dotfiles --skill read-book-mintuz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Reading long books and retaining their content is time-consuming, and manually organizing chapter notes, quotes, and takeaways into a reusable knowledge base is tedious. This Skill automates chunked reading and structured note extraction from books and long documents. ## Core Features & Use Cases - Multi-format ingestion: Reads PDF, EPUB, MOBI, Markdown, plain text, pasted text, and public-domain URLs, converting EPUB/MOBI via pandoc or calibre. - Four extraction modes: notes (chapter-by-chapter TL;DR, concepts, quotes, action items, frameworks), summary (whole-book TL;DR plus takeaways), quotes (verbatim pull-quotes with page refs), and study (notes plus spaced-repetition Q&A cards). - Smart chunking: Splits by chapter when a TOC exists, by 50-page blocks for PDFs, or by 30,000-character blocks for text, saving a chunking plan as JSON. - Second-brain capture: Optionally writes the final notes to a second-brain vault as a highlights file with wiki cross-reference suggestions, and can render output to PDF or HTML via pandoc. - Use Case: You have a 300-page business book PDF. Run the notes mode to get per-chapter summaries, verbatim quotes with page numbers, and action items, then capture the result into your Obsidian vault for later compilation into wiki pages. ## Quick Start Ask the assistant to read the book at a given file path and extract chapter-by-chapter notes with key takeaways and quotes.

Frequently Asked Questions about read-book

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract notes from a PDF book chapter by chapter?▼

Provide the PDF path and the Skill detects the table of contents using pdfinfo and pdftotext, then reads the book in chapter-sized chunks. Each chunk produces a TL;DR, key concepts, verbatim quotes, action items, and frameworks, aggregated into one notes file.

What tools convert EPUB or MOBI files to readable text?▼

EPUB files convert to Markdown with pandoc, preserving chapter headers for chunking. MOBI and AZW3 files require calibre's ebook-convert, which can output EPUB or plain text before further processing.

Can I generate spaced-repetition flashcards from a book?▼

Yes, study mode produces standard chapter notes plus 2-4 Q&A pairs per chapter, aggregated into a full deck of 10-20 cards. The output is formatted for direct import into Anki, Mochi, or RemNote.

Does PDF reading work with scanned documents without a text layer?▼

Scanned PDFs need OCR first. Install ocrmypdf via Homebrew and run it on the file to add a text layer, then proceed with normal chunked reading and extraction.

What are the limitations when reading very long books?▼

The PDF reader handles roughly 10 pages per call, so books over 200 pages require many chunked reads. For books over 500 pages the Skill warns about cost and time and suggests summary mode instead of full notes.

Related Skills

Explore More Education & Research Skills→
xberg-ioxberg-io
26

extracting-with-ocr

Extract machine-readable text from scanned PDFs and images using OCR engines.

Official
Advanced
coreyhaines31coreyhaines31
552

second-brain

Capture, compile, query, and lint markdown-based Second Brain vaults.

Community
Advanced
MOODMNKY-LLCMOODMNKY-LLC

youtube-transcriber-selfhosted

Automate YouTube transcript retrieval, search, and enrichment workflows.

Community
Intermediate
812lcl812lcl

readwise-cli

Access and search Readwise highlights and Reader documents from the command line.

Community
Intermediate