book-to-skill

name	book-to-skill
description	Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through Amp or Claude Code, apply an author's frameworks while working, or build a reusable knowledge base from a file.
compatibility	Amp skill directories (.agents/skills, ~/.config/agents/skills, ~/.config/amp/skills) and Claude Code skill directories (~/.claude/skills).
allowed-tools	["shell_command","Read","Write","Glob","Grep"]
argument-hint	<path-to-document> [skill-name-slug]

Book-to-Skill Converter

Transform written knowledge into actionable agent skills by extracting structure — not producing summaries.

Philosophy

Books contain crystallized expertise: frameworks, principles, and techniques that took years to develop. This skill extracts that knowledge into a format Amp, Claude Code, or another compatible agent can leverage repeatedly.

Extract structure, not summaries. A skill isn't a book report. It's a toolkit of:

• Named frameworks (mental models with clear application)
• Actionable principles (rules that guide decisions)
• Techniques (step-by-step methods)
• Anti-patterns (what to avoid and why)
• Voice calibration (how the author thinks and communicates)

Preserve the author's precision. Frameworks often have specific names for reasons. "The 5 Whys" isn't interchangeable with "ask why multiple times." Capture the exact formulation.

Layer depth appropriately. Simple books → simple skills. Complex books with 10+ frameworks → skills with reference files and on-demand chapters.

---

Modes of Operation

Three paths available. Route based on what the user asks:

1. Full Conversion (Default)

Trigger: User provides a supported document path without special instructions Action: Run all steps below (Steps 0–9) Output: Complete skill with SKILL.md, chapters/, glossary, patterns, cheatsheet

2. Analyze Only

Trigger: User says "analyze", "just extract", or "I want to review before generating" Action: Run Steps 0–3, then produce a structured extraction report (frameworks, principles, techniques found). Stop — do NOT generate skill files. Output: Analysis report for user review

3. Generate from Prior Analysis

Trigger: User has existing analysis notes or previously ran analyze-only Action: Skip Steps 0–3, use the provided analysis as input, run Steps 4–9 Output: Skill files from the provided analysis

---

Skill Locations

This converter can run from multiple skill systems. When looking for this converter's helper script or writing the generated book skill, prefer these locations in order:

1. Amp project-local skills: .agents/skills/
2. Amp global skills: ~/.config/agents/skills/
3. Amp legacy global skills: ~/.config/amp/skills/
4. Claude Code skills: ~/.claude/skills/

Generated skills should default to ~/.config/agents/skills/ for Amp unless the user asks for project-local or Claude Code output.

---

Step 0 — Out-of-scope check

If the argument is NOT a path to a supported document file, stop and respond:

"book-to-skill requires a supported document path. Usage: book-to-skill /path/to/book.pdf [skill-name], book-to-skill /path/to/book.epub [skill-name], or another supported format such as .docx, .md, .txt, .html, .rtf, .mobi, or .azw3."

Throughout the workflow, treat the first argument as BOOK_PATH and the optional second argument as SKILL_NAME.

---

Step 1 — Validate input

test -f "$BOOK_PATH" && echo "FILE_OK" || echo "FILE_NOT_FOUND: $BOOK_PATH"
case "${BOOK_PATH##*.}" in
  pdf|PDF|epub|EPUB|docx|DOCX|txt|TXT|md|MD|markdown|MARKDOWN|rst|RST|adoc|ADOC|asciidoc|ASCIIDOC|html|HTML|htm|HTM|rtf|RTF|mobi|MOBI|azw|AZW|azw3|AZW3) echo "FORMAT_OK" ;;
  *) echo "FORMAT_UNKNOWN" ;;
esac

Check the file extension (.pdf, .epub, .docx, .txt, .md, .markdown, .rst, .adoc, .html, .htm, .rtf, .mobi, .azw, .azw3) or magic bytes (%PDF or PK zip header for EPUB/DOCX).

If the file is not found or the format is not supported, stop with a clear error message listing supported formats.

---

Step 1.5 — Identify book type

Before extracting, ask the user:

"What kind of content does this book have? This helps me choose the best extraction method.

1. Technical — has code blocks, tables, formulas, diagrams (e.g. programming books, academic papers, architecture guides)
2. Text-heavy — mostly prose, few or no tables/code (e.g. management, productivity, narrative non-fiction)
3. Not sure — I'll use the fast method and warn you if quality seems limited"

Store the answer as BOOK_TYPE:

• Option 1 → BOOK_TYPE=technical
• Option 2 → BOOK_TYPE=text
• Option 3 → BOOK_TYPE=text

If BOOK_TYPE=technical, inform the user before proceeding:

"📐 Technical mode selected — using Docling for structure-aware extraction (tables, code blocks, formulas preserved as markdown). This takes ~1.5s per page, so expect a few minutes for longer books. Starting now…"

If BOOK_TYPE=text, inform:

"📄 Text mode selected — using the fastest suitable extractor for this file type. Plain text/Markdown/HTML are usually ready in seconds; PDFs use pdftotext when available."

---

Step 2 — Extract text from the source document

Run the extraction script, passing the book type:

SCRIPT_PATH=""
for candidate in \
  ".agents/skills/book-to-skill/scripts/extract.py" \
  "$HOME/.config/agents/skills/book-to-skill/scripts/extract.py" \
  "$HOME/.config/amp/skills/book-to-skill/scripts/extract.py" \
  "$HOME/.claude/skills/book-to-skill/scripts/extract.py"
do
  if [ -f "$candidate" ]; then
    SCRIPT_PATH="$candidate"
    break
  fi
done

if [ -z "$SCRIPT_PATH" ]; then
  echo "Could not find scripts/extract.py for book-to-skill" >&2
  exit 1
fi

PYTHON_BIN="${PYTHON_BIN:-python3}"
if ! command -v "$PYTHON_BIN" >/dev/null 2>&1; then
  PYTHON_BIN="python"
fi

"$PYTHON_BIN" "$SCRIPT_PATH" "$BOOK_PATH" --mode <BOOK_TYPE> --install-missing ask

Before extraction, the script checks optional Python packages needed for the detected format. If a better extractor is missing, it prompts the user with the available fallback, for example:

"DOCX extraction uses python-docx if installed, otherwise a stdlib ZIP/XML parser. Missing package(s) detected. Do you want to install? y=install, n=fallback"

Use --install-missing yes to install missing Python packages without prompting, --install-missing no or --no-install-missing to always use fallbacks, or BOOK_SKILL_INSTALL_MISSING=yes|no|ask to set the behavior by environment variable. Non-interactive sessions default to fallback unless install mode is explicitly yes.

• PDF --mode technical → uses Docling (layout-aware, preserves tables and code blocks as markdown)
• PDF --mode text → uses pdftotext → PyPDF2 → pdfminer fallback chain (fast, plain text)
• EPUB → uses ebooklib + BeautifulSoup4, then stdlib ZIP/HTML fallback
• DOCX → uses python-docx, then stdlib ZIP/XML fallback
• TXT/Markdown/reStructuredText/AsciiDoc → reads directly as text
• HTML → uses BeautifulSoup4, then stdlib HTML fallback
• RTF → uses striprtf, then a basic regex fallback
• MOBI/AZW/AZW3 → uses Calibre ebook-convert when installed. Calibre is an external app, not a pip package, so the script reports how to install it if missing.

This creates:

• <tempdir>/book_skill_work/full_text.txt — full extracted text
• <tempdir>/book_skill_work/metadata.json — title, estimated pages, token count, size, extraction_mode

Read the output_text path in <tempdir>/book_skill_work/metadata.json to understand what was extracted. The extractor uses the platform temp directory by default and supports BOOK_SKILL_WORKDIR if an explicit work directory is needed.

---

Step 2.5 — Pre-flight cost estimate

Read <tempdir>/book_skill_work/metadata.json and present the user with an estimate before doing any generation:

📖 Source detected: <filename> (<format>)
📄 Pages/Spine items/Sections: ~<N> | Words: ~<N> | Source tokens: ~<N>K

💰 Estimated token cost (Full Conversion):
   Input  (book reading + prompts): ~<N>K tokens
   Output (skill files generated):  ~<N>K tokens
   Total:                           ~<N>K tokens

   Reference prices (as of 2025):
   Claude Sonnet 4.5 → ~$<X> USD
   Claude Haiku 4.5  → ~$<X> USD

   ⏱  Estimated time: ~<N> minutes

📁 Files to be generated:
   SKILL.md + <N> chapter files + glossary + patterns + cheatsheet

➡  Proceed with Full Conversion? (or type "analyze only" to preview first)

How to estimate:

• Input tokens ≈ estimated_tokens from metadata × 1.3 (prompts overhead per chapter pass)
• Output tokens ≈ chapters × 1,000 + 4,000 (SKILL.md) + 4,500 (glossary + patterns + cheatsheet)
• Price: Sonnet input=$3/MTok output=$15/MTok — Haiku input=$0.80/MTok output=$4/MTok

Wait for the user to confirm before proceeding. If they say "analyze only", switch to Mode 2.

---

Step 2.6 — REPL-style access for large books (> 50k tokens)

Inspired by the Recursive Language Model (RLM) paradigm: treat full_text.txt as a queryable corpus, not a single read. Loading the whole file into context burns budget you will need later for generation.

For books over ~50k tokens, prefer programmatic probes over Read(full_text.txt) without bounds:

# Size check before any Read
wc -w "$FULL_TEXT_PATH"

# Find chapter offsets without loading the whole file
grep -n -E "^\s*(Chapter|CHAPTER)\s+[0-9]+" "$FULL_TEXT_PATH" | head -40

# Pull only the chapter you need (lines start..end inclusive)
sed -n '<start>,<end>p' "$FULL_TEXT_PATH"

# Verify a framework is actually mentioned before claiming it in SKILL.md
grep -c -i "westrum\|dora" "$FULL_TEXT_PATH"

# Targeted Read with offset/limit avoids dumping the full file
# Read(file_path=full_text.txt, offset=<line>, limit=<lines>)

Use this approach for Step 3 (structure analysis), Step 7 (per-chapter summaries), and Step 8 (glossary / patterns extraction). On books under 50k tokens, a single Read is fine.

Why this matters: a 200-page book is ~75k tokens. Re-reading it once per chapter (28 passes) costs ~2M input tokens; using grep + sed to pull only relevant slices keeps generation cost proportional to the output, not the source.

---

Step 3 — Analyze book structure

Read the first 8,000 characters of the extracted full_text.txt to identify:

• Book title and author(s)
• Chapter structure (look for "Chapter N", "PART I", numbered headings, table of contents)
• Core themes and subject domain
• Approximate number of chapters

Then read the Table of Contents section if present to map all chapters.

If mode is "Analyze Only": produce the extraction report now and stop. Structure:

## Extraction Report — <Title>

### Author's Core Frameworks
- **<Framework Name>**: <what it is and when to apply>

### Key Principles
- <Principle>: <actionable rule>

### Techniques & Methods
- <Technique>: <step-by-step or how-to>

### Anti-patterns
- <What to avoid>: <why>

### Suggested Skill Name
`{author-lastname}-{core-concept}` — e.g. `cialdini-influence`

### Chapters Detected
| # | Title | Main Frameworks |

---

Step 4 — Ask purpose (Full Conversion only)

Before generating, ask the user:

"What should this skill help you do? (Pick one or more)

1. Apply the author's frameworks while working
2. Think with the author's mental models
3. Reference specific chapters and concepts
4. All of the above"

Use the answer to weight what gets highlighted in the SKILL.md Core section.

---

Step 5 — Determine skill name

If SKILL_NAME was provided, use it as the skill slug. Otherwise, propose two options and let the user choose:

• By author-concept: {author-lastname}-{core-concept} (e.g. cialdini-influence, meadows-systems)
• By title: lowercase hyphens from book title (e.g. designing-data-intensive-apps)

Default to author-concept format if the book has a strong methodological identity.

Choose the destination skill root:

• Amp default: ~/.config/agents/skills
• Amp project-local: .agents/skills when the user explicitly wants the generated book skill scoped to the current workspace
• Amp legacy: ~/.config/amp/skills if that is the user's existing global skill location
• Claude Code: ~/.claude/skills if the user explicitly asks for Claude Code output

Set SKILLS_HOME to the selected root and check that $SKILLS_HOME/<skill_name>/ does NOT already exist. If it does, append -2 or ask the user before overwriting.

---

Step 6 — Create skill directory structure

mkdir -p "$SKILLS_HOME/<skill_name>/chapters"

---

Step 7 — Generate chapter summaries

TOKEN BUDGET RULE — CRITICAL:

• Each chapter summary file: 800–1,200 tokens (dense, not verbose)
• Files are loaded on-demand — they are NOT capped per se, but keep them useful and tight

For EACH chapter/major section identified in Step 3:

Read the corresponding section of the extracted full_text.txt (use character offsets or grep for chapter headings).

Create $SKILLS_HOME/<skill_name>/chapters/ch<NN>-<slug>.md using the structure below.

Adapt emphasis based on BOOK_TYPE:

• technical → prioritize "Code Examples", "Reference Tables", and "Commands & APIs" sections; preserve exact syntax
• text → prioritize "Frameworks Introduced", "Mental Models", and "Key Takeaways"; skip empty technical sections

# Chapter N: <Full Title>

## Core Idea
<1–2 sentences: the single most important thing this chapter teaches>

## Frameworks Introduced
- **<Framework Name>**: <exact formulation — preserve the author's naming>
  - When to use: <specific situation>
  - How: <steps or criteria>

## Key Concepts
- **<Term>**: <precise definition in 1 sentence>
(5–10 most important terms from this chapter)

## Mental Models
<2–4 frameworks or thinking tools. Write as "Use X when Y" or "Think of X as Y">

## Anti-patterns
- **<What to avoid>**: <why it fails>

## Code Examples *(technical books only — omit if BOOK_TYPE=text)*
<!-- Copy the most instructive snippet from the chapter. Preserve indentation exactly. -->
```<language>
<key code example from this chapter>

• What it demonstrates:

Reference Tables (technical books only — omit if BOOK_TYPE=text)

Key Takeaways

(3–7 takeaways a practitioner must remember)

Connects To

• Ch N:
• :

---

## Step 8 — Generate supporting files

### glossary.md
Create `$SKILLS_HOME/<skill_name>/glossary.md`:
- Every significant term from the book, alphabetically sorted
- Format: `**Term** — definition (Ch N)`
- Max 1,500 tokens

### patterns.md
Create `$SKILLS_HOME/<skill_name>/patterns.md`:
- All concrete techniques, design patterns, algorithms from the book
- Format: `## Pattern Name\n**When to use**: ...\n**How**: ...\n**Trade-offs**: ...`
- Max 2,000 tokens

### cheatsheet.md
Create `$SKILLS_HOME/<skill_name>/cheatsheet.md`:
- Decision tables, comparison matrices, quick-reference rules
- The content you'd want on a single printed page
- Max 1,000 tokens

---

## Step 9 — Generate the master SKILL.md

**CRITICAL TOKEN BUDGET: Keep SKILL.md body under 4,000 tokens.**
Compaction truncates from the END — put the most important content FIRST.

Create `$SKILLS_HOME/<skill_name>/SKILL.md`:

```markdown
---
name: <skill_name>
description: "Knowledge base from \"<Full Title>\" by <Author(s)>. Use when applying <author>'s frameworks for <key topics, 3–6 terms>, studying the book, or referencing its concepts."
allowed-tools:
  - Read
  - Grep
argument-hint: [topic, framework name, or chapter number]
---

# <Full Title>
**Author**: <Author(s)> | **Pages**: ~<N> | **Chapters**: <N> | **Generated**: <YYYY-MM-DD>

## How to Use This Skill

- **Without arguments** — load core frameworks for reference
- **With a topic** — ask about `replication`, `pricing`, or another indexed topic; I find and read the relevant chapter
- **With chapter** — ask for `ch05`; I load that specific chapter
- **Browse** — ask "what chapters do you have?" to see the full index

When you ask about a topic not covered in Core Frameworks below, I will read
the relevant chapter file before answering.

---

## Core Frameworks & Mental Models
<!-- ~2,000 tokens: the author's most important named frameworks and principles.
     Preserve exact names. Write as "Use X when Y", "Prefer X over Y because Z".
     This is a toolkit, not a summary. -->

<generate 2,000 tokens of the most critical frameworks and insights here>

---

## Chapter Index

| # | Title | Key Frameworks |
|---|-------|----------------|
| [ch01](chapters/ch01-<slug>.md) | <Title> | <framework1>, <framework2> |
| [ch02](chapters/ch02-<slug>.md) | <Title> | <framework1>, <framework2> |
...

## Topic Index

<!-- Alphabetical. Major terms/frameworks → chapter(s) that cover them. -->
- **<Term>** → ch<N>[, ch<N>]
- **<Term>** → ch<N>

## Supporting Files

- [glossary.md](glossary.md) — all key terms with definitions
- [patterns.md](patterns.md) — all techniques and design patterns
- [cheatsheet.md](cheatsheet.md) — quick reference tables and decision guides

---

## Scope & Limits

This skill covers the book content only. For hands-on implementation in your codebase,
combine with project-specific tools. For topics beyond this book, check related skills
or ask the agent directly.

---

Step 10 — Cleanup and report

PYTHON_BIN="${PYTHON_BIN:-python3}"
if ! command -v "$PYTHON_BIN" >/dev/null 2>&1; then
  PYTHON_BIN="python"
fi

"$PYTHON_BIN" - <<'PY'
import os
import shutil
import tempfile
from pathlib import Path
shutil.rmtree(
    os.environ.get("BOOK_SKILL_WORKDIR", Path(tempfile.gettempdir()) / "book_skill_work"),
    ignore_errors=True,
)
PY

Then report to the user:

✅ Skill created: $SKILLS_HOME/<skill_name>/

📚 Book: <Full Title> — <Author>
📄 Pages: ~<N> | Chapters: <N>

Files generated:
  SKILL.md         — core frameworks + index   (~X tokens)
  chapters/        — <N> chapter summaries     (~X tokens each, ~X total)
  glossary.md      — key terms                 (~X tokens)
  patterns.md      — techniques & patterns     (~X tokens)
  cheatsheet.md    — quick reference           (~X tokens)
  ─────────────────────────────────────────────────────
  Total skill size: ~X tokens (loaded on-demand, not all at once)

💡 Tip: check your agent's session cost/usage command to see actual token usage.

Usage:
  Ask for <skill_name>                  → load core frameworks
  Ask <skill_name> about <topic>        → find and explain a topic
  Ask <skill_name> for ch<N>            → dive into a specific chapter

---

Quality Rules

1. Extract structure, not summaries — capture named frameworks, exact formulations, anti-patterns; not chapter recaps
2. Preserve the author's precision — "The 5 Whys" ≠ "ask why multiple times"; keep exact naming
3. Density over completeness — a 1,000-token summary beats a 10,000-token excerpt
4. Practitioner voice — write "Use X when Y", not "The book explains X"
5. Front-load SKILL.md — compaction keeps the first 5,000 tokens; most important content comes first
6. Chapter files are on-demand — they don't count against skill budget until loaded
7. Never copy raw book text — always synthesize, summarize, extract signal
8. Topic index is critical — it's how the agent navigates to the right chapter file