Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add apple-ouyang/book-to-skill --skill book-to-skillgit clone --depth 1 https://github.com/apple-ouyang/book-to-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/apple-ouyang/book-to-skill/book-to-skill)<a href="https://agentmods.dev/skills/apple-ouyang/book-to-skill/book-to-skill"><img src="https://agentmods.dev/badge/skills/apple-ouyang/book-to-skill/book-to-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/apple-ouyang/book-to-skill/book-to-skill"><img src="https://agentmods.dev/badge/skills/apple-ouyang/book-to-skill/book-to-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01684 |
| Opus 5.5 | $0.00020 | $0.00674 |
| Sonnet 5.5 | $0.00010 | $0.00337 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
book-to-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
拆书：从书籍到可执行 Skill
任务目标
把一本书中的核心框架、操作方法和真实案例，拆解成结构化的 Claude Code Skill，让 AI Agent 能在用户需要时自动调用书中的智慧。
前置依赖
- PDF Skill：用于读取 PDF 格式书籍（
npx @anthropic-ai/claude-code-skills install pdf） - Swarm Skill：用于多 Agent 并行处理不同章节（当书籍超出单 Agent 上下文窗口时必须使用）
第一步：评估书籍规模，决定单 Agent 还是多 Agent
这是最关键的一步。 在开始拆书之前，必须先估算书籍内容是否能装进单个 Agent 的上下文窗口。
上下文窗口容量（按 100k token 估算）
| 语言 | 100k token ≈ | 扣除格式开销后 |
|---|---|---|
| 英文 | ~75,000 单词 / ~270 页 | ~200 页 |
| 中文 | ~50,000-65,000 字 / ~110 页 | ~80 页 |
注：上下文窗口不只装书的内容，还要装 Skill 指令、Agent 提示词、输出缓冲等。所以实际可用于书籍内容的空间约为窗口的 70-80%。
操作：估算 PDF 页数
# 用 PDF Skill 读取页数
# 或者直接问用户：这本书大概多少页？
决策树
书籍页数？
├── 英文 ≤ 200 页 / 中文 ≤ 80 页
│ → 单 Agent 模式（直接读取全书，一个 Agent 完成所有提取）
│
├── 英文 200-500 页 / 中文 80-200 页
│ → Swarm 模式：2-3 个 Agent，每个负责一部分章节
│
└── 英文 > 500 页 / 中文 > 200 页
→ Swarm 模式：4-6 个 Agent，按主题/部分拆分
Agent 数量计算公式
所需 Agent 数 = ceil(书籍页数 / 单 Agent 可处理页数)
单 Agent 可处理页数：
- 英文：~200 页
- 中文：~80 页
示例：《行为设计学》中文版约 250 页 → ceil(250 / 80) = 4 个 Agent，实际拆成了 4 个 Skill（making-decisions + 3 个子 Skill），每个 Agent 负责 2-3 章。
第二步：通读目录，识别框架骨架
读取书籍目录和前言（这一步不需要读全书，单 Agent 即可），回答：
- 这本书解决什么核心问题？
- 作者提出的主框架是什么？（如 WRAP、OODA、第一性原理）
- 框架有几个核心步骤/模块？
- 每个步骤对应哪些章节？
输出：框架骨架表
| 框架步骤 | 对应章节 | 预计拆成的 Skill | 分配给 Agent |
|---------|---------|----------------|-------------|
| 步骤 1 | 第 1-3 章 | skill-name-1 | Agent 1 |
| 步骤 2 | 第 4-6 章 | skill-name-2 | Agent 2 |
第三步：确定 Skill 结构
根据框架复杂度决定：
- 单 Skill：框架简单，3-5 个步骤，一个 SKILL.md 搞定
- 主 Skill + 子 Skill：框架复杂，每个步骤本身就是一套方法论
- 主 Skill 负责路由（判断用户场景 → 调度子 Skill）
- 子 Skill 负责具体操作
判断标准：如果一个步骤的操作说明超过 100 行，就应该拆成独立子 Skill。
第四步：逐章提取
单 Agent 模式
直接读取全书 PDF，按章节顺序提取。
Swarm 多 Agent 模式
用 /swarm 启动团队，按第二步的分配表分配章节。
Agent 提示词模板：
角色：章节提取员
职责：阅读第 X-Y 章（PDF 第 M-N 页），按以下格式提取内容
提取内容：
1. 核心概念（一句话总结）
2. 操作步骤（具体可执行，不是"思考一下"，而是"问自己：___"）
3. 案例（格式：人物/组织 → 情境 → 做法 → 结果 → 启示）
4. 警惕信号（什么情况下应该触发这个方法）
5. 注意事项（边界情况、常见误用）
输出要求：Markdown 格式，每章一个二级标题
完成标准：每章至少 2 个案例，操作步骤必须具体到 Agent 可以直接执行
文件范围：只读取 PDF 第 M-N 页，不要读其他部分
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 176 lines · 51 tokens per session scan A a8f086ea969c
book-to-skill is a skill published in the GitHub repository apple-ouyang/book-to-skill (174 stars, last pushed 8mo ago), licensed MIT. It adds 51 tokens to every session and 1,684 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.