Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Book To Skill

ASecurity

Use when turning books, PDFs, e-books, docs into conversable Agent Skills — on-demand chapter fragments, 50x fewer tokens, cleaning diagram dirt, technical vs text-heavy. Triggers on "transformar livro em skill", "PDF em skill", "book to skill", "livro em skill", "fragmentos de livro", "50x tokens", "virgilio book-to-skill".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythongobashgitapiperformance

Works with

claude codecursorcliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill book-to-skill --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Book To Skill?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Book To Skill
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-book-to-skill/badge)](https://www.skillsdirectory.com/skills/majinmagros-book-to-skill)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: book-to-skill
description: Use when turning books, PDFs, e-books, docs into conversable Agent Skills — on-demand chapter fragments, 50x fewer tokens, cleaning diagram dirt, technical vs text-heavy. Triggers on "transformar livro em skill", "PDF em skill", "book to skill", "livro em skill", "fragmentos de livro", "50x tokens", "virgilio book-to-skill".
metadata:
  origin: ECC
---

# Skill: Book to Skill (livro → skill on-demand)

Transforme qualquer livro/PDF/e-book em uma **Agent Skill** conversável que responde on-demand via fragmentos, sem carregar o livro inteiro. Validado contra `https://github.com/virgiliojr94/book-to-skill` (24.6k★ MIT, 2026-08-23) — `XJOMq3KlzSE.pt.dedup.txt:117`.

## Quando usar

- Precisa consultar um livro técnico ou de literatura sem estourar contexto/tokens.
- Quer 24×–51× menos tokens por query vs jogar PDF inteiro no contexto (`docs/performance.md`).
- Tem PDFs/EPUB/DOCX/MD/HTML/RTF/MOBI com tabelas, gráficos ou código que precisam de limpeza de diagramação.
- Quer skill reutilizável no padrão *Agent Skills* (`agentskills/agentskills`) em Claude Code/Codex/Cursor/VS Code.

Não use para: RAG de código (isso é `graphify`); ledger cronológico de contexto disperso (isso é `context-ledger`); conversão comercial com API paga (isso é `nutrient-document-processing`).

## Conceitos-chave (do repo oficial)

- **On-demand / fragmentos**: skill carrega `SKILL.md` (~4k) + 1 capítulo (~1k) por query = ~5k vs 120k+ do dump → 24× (Think Python 2) a 51× (AI Engineering) fewer tokens — `https://github.com/virgiliojr94/book-to-skill/blob/master/docs/performance.md`
- **Limpeza de diagramação**: extrai texto, limpa sujeira de diagramação, entrega texto limpo `XJOMq3KlzSE.pt.dedup.txt:84`
- **Técnico vs texto corrido**: se técnico (gráficos/tabelas/código) → `docling` (~1.5s/pg, preserva tabelas/código, mais lento/cuidadoso) `XJOMq3KlzSE.pt.dedup.txt:88`; se texto corrido → `pdftotext` (instant) — escolha no `extract.py`
- **Estimativa de custo + quebra em capítulos + manual** `XJOMq3KlzSE.pt.dedup.txt:108` → gera `chapters/ch*.md`, `glossary.md`, `patterns.md`, `cheatsheet.md`
- **Formatos**: PDF/EPUB/DOCX/MD/HTML/RTF/MOBI+A (com `pip install` extra) — `docs/how-it-works.md` Steps 0-10

## Passo a passo

### 1. Instale

Repositório oficial `https://github.com/virgiliojr94/book-to-skill`:

```bash
# via Agent Skills (preferido)
npx skills add virgiliojr94/book-to-skill
# → Claude Code: ~/.claude/skills/book-to-skill/
# → Copilot CLI: ~/.copilot/skills/
# → Amp: ~/.agents/skills/

# ou clone direto
git clone https://github.com/virgiliojr94/book-to-skill.git
cd book-to-skill && pip install -r requirements.txt
# para técnico: pip install docling
```

Docs: `https://github.com/virgiliojr94/book-to-skill/blob/master/docs/install.md`

### 2. Escolha técnico vs texto

O `extract.py` pergunta: "Is this technical (tables/code/diagrams) or text-heavy?" `XJOMq3KlzSE.pt.dedup.txt:88`
- **Texto corrido** (romance, filosofia — ex: `Plato Republic` 289p `XJOMq3KlzSE.pt.dedup.txt:312`) → `pdftotext`
- **Técnico** (livros com gráficos/tabelas) → `docling` (valide com `python3 scripts/extract.py --check`)

### 3. Extraia e gere a skill

```bash
# modo skill (gera ~/.claude/skills/<nome>/)
/book-to-skill <path|folder|glob> [skill-name]
# ou direto
python3 scripts/extract.py <livro.pdf> --skill-name plato-republic

# só analisar (estimativa tokens/tempo/custo sem gerar)
python3 scripts/extract.py <livro.pdf> --analyze-only

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →