read-book

1# /read-book — Extract structured notes from books and long PDFs
2 
3Sibling to `watch-video`. Same content-consumption pattern: ingest → chunk → extract → optionally capture to second-brain.
4 
5## Step 1 — Parse input
6 
7Accept:
8- **PDF**: file path (Claude reads PDFs natively in chunks via `Read pages:"X-Y"`)
9- **EPUB / MOBI**: file path (needs `pandoc` or `ebook-convert` to extract — see `references/sources.md`)
10- **Markdown / .txt**: file path (read directly)
11- **Pasted text**: just use what was pasted
12- **URL** to public-domain text: fetch it with your agent's URL-fetch tool or `curl` (Project Gutenberg, archive.org, etc.)
13 
14Detect type from file extension. If ambiguous, ask.
15 
16## Step 2 — Parse mode
17 
18| Invocation | Mode | What you get |
19|---|---|---|
20| `/read-book <input>` | **notes** (default) | Chapter-by-chapter: TL;DR + key concepts + quotes + action items + frameworks |
21| `/read-book <input> summary` | summary | Whole-book TL;DR (1 paragraph) + 3–5 key takeaways + who-it's-for |
22| `/read-book <input> quotes` | quotes | Pull-quote highlights only, with chapter context and page refs |
23| `/read-book <input> study` | study | Notes mode + 10–20 spaced-repetition Q&A cards |
24 
25If the book is long (>200 pages) and mode is unspecified, default to `notes` but warn it'll take many tool calls.
26 
27## Step 3 — Get the text + chunk
28 
29See `references/sources.md` for per-source ingestion. Output of this step: text content + a chunking plan.
30 
31**Chunking strategy** (hybrid, in priority order):
32…