/read-book, Extract structured notes from books and long PDFs

Sibling to watch-video. Same content-consumption pattern: ingest → chunk → extract → optionally capture to second-brain.

Step 1, Parse input

Accept:

• PDF: file path (Claude reads PDFs natively in chunks via Read pages:"X-Y")
• EPUB / MOBI: file path (needs pandoc or ebook-convert to extract, see references/sources.md)
• Markdown / .txt: file path (read directly)
• Pasted text: just use what was pasted
• URL to public-domain text: fetch it with your agent's URL-fetch tool or curl (Project Gutenberg, archive.org, etc.)

Detect type from file extension. If ambiguous, ask.

Step 2, Parse mode

Invocation	Mode	What you get
/read-book <input>	notes (default)	Chapter-by-chapter: TL;DR + key concepts + quotes + action items + frameworks
/read-book <input> summary	summary	Whole-book TL;DR (1 paragraph) + 3, 5 key takeaways + who-it's-for
/read-book <input> quotes	quotes	Pull-quote highlights only, with chapter context and page refs
/read-book <input> study	study	Notes mode + 10, 20 spaced-repetition Q&A cards

If the book is long (>200 pages) and mode is unspecified, default to notes but warn it'll take many tool calls.

Step 3, Get the text + chunk

See references/sources.md for per-source ingestion. Output of this step: text content + a chunking plan.

Chunking strategy (hybrid, in priority order):

1. By chapter if a TOC exists (PDF with bookmarks, EPUB/MOBI converted via pandoc preserves chapter headers)

   • Use pdfinfo <pdf> | grep "Pages" for PDFs
   • Use pdftotext -layout <pdf> | grep -i "^chapter\|^part" for chapter detection, or read TOC from page 1, 5
   • EPUB: after pandoc <epub> -o tmp.md, chunks are between # Chapter X headers

2. By page count for PDFs without TOC: 50 pages per chunk