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 fanyty/claude-distill-book --skill distill-bookgit clone --depth 1 https://github.com/fanyty/claude-distill-bookWrote 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/fanyty/claude-distill-book/distill-book)<a href="https://agentmods.dev/skills/fanyty/claude-distill-book/distill-book"><img src="https://agentmods.dev/badge/skills/fanyty/claude-distill-book/distill-book/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/fanyty/claude-distill-book/distill-book"><img src="https://agentmods.dev/badge/skills/fanyty/claude-distill-book/distill-book.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 | $0.00113 | $0.01979 |
| Opus 5 | $0.00056 | $0.00989 |
| Sonnet 5 | $0.00023 | $0.00396 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
distill-book scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
书籍蒸馏 Skill
将 PDF 书籍蒸馏为一个结构化、可验证的 Claude Code Skill 目录。本 Skill 整合了 book-distill、daizhouchen/book-distiller、bookforge-ai、edgarmrueda-alt 等社区 优秀实践。
蒸馏流程（7 步）
Step 1: 收集输入信息
向用户确认：
- 源路径：PDF 文件或已转换的 Markdown 目录
- Skill 名称：英文，小写+连字符（如
system-design-guide） - 安装位置：
- 全局：
~/.claude/skills/<name>/（推荐） - 项目本地：
.claude/skills/<name>/
- 全局：
- 是否多书合成：如果是追加到已有 Skill，需做 overlap 分析
Step 2: 解析源文件
# 优先 marker-pdf（保留结构和表格）
marker_single "$PDF_PATH" --output_dir /tmp/book-markdown
# 备选 pdfplumber（marker 不可用时）
python3 ${CLAUDE_SKILL_DIR}/scripts/pdf_to_md.py "$PDF_PATH" /tmp/book-markdown
Step 3: 原型识别（关键新增）
阅读目录、前言、前 2-3 章，判定书籍原型，不同原型采用不同提取策略和 SKILL.md 骨架：
| 原型 | 特征 | 提取策略 | SKILL.md 骨架 |
|---|---|---|---|
| 工具书 (Tool) | 教程、手册、参考 | 工作流 + 决策树 + 常见陷阱 | 概述/原则/工作流/决策/陷阱/参考 |
| 思想书 (Philosophy) | 哲学、理论、 manifesto | 核心论点 + 心智模型 + 反直觉洞察 | 概述/论点/模型/反思/参考 |
| 叙事书 (Narrative) | 传记、案例、故事 | 关键事件 + 决策点 + 教训 | 概述/时间线/决策/教训/参考 |
| 技能书 (Skill) | 实操、练习、方法论 | 步骤 + 检查点 + 反模式 | 概述/方法/步骤/检查点/反模式/参考 |
特别提醒：思想书禁止"4 周行动计划"——思想是内化不是执行。叙事书禁止抽象原则堆砌——保留具体情节。
Step 4: 事实系统化四步法（关键新增）
对每章按以下四步提取，避免挑选事实导致以偏概全：
4.1 维度分类（穷尽式提取）
收集五类事实，包括沉默性事实：
- 情节 - 发生了什么
- 言论 - 作者/人物说了什么
- 数据 - 数字、统计、引用
- 结构 - 组织方式、分类框架
- 沉默 - 作者没说什么、避开了什么、盲区在哪里（最重要，揭示作者局限）
4.2 模式识别
跨章节找重复出现的模式、对比、因果链。
4.3 跨维度交织
将不同维度的事实交叉验证：言论是否与情节一致？数据是否支持结构？
4.4 可视化
用表格、决策树、时间线呈现交织结果。
Step 5: 信源分级（关键新增）
每条知识标注信源等级，产出文件头部声明信源构成：
| 等级 | 来源 | 置信度 |
|---|---|---|
| A | 原书直接引用 | 高 |
| B | 学术文献/论文 | 高 |
| C | 书评/二手解读 | 中 |
| D | 模型补充知识 | 低（需标注） |
Fidelity Statement 模板（放在 SKILL.md 概述之后）：
## 信源声明
- A 级（原书直接提取）：XX%
- B 级（学术补充）：XX%
- C 级（解读）：XX%
- D 级（模型知识）：XX%
- 编辑编译：全部 / 部分
Step 6: 结构化决策点（关键新增）
根据书籍规模和内容，决定输出结构：
书籍 < 10 章 且 主题单一？
├── 是 → 单一 SKILL.md + reference/chXX.md
└── 否 → 评估以下决策：
├── 主题跨多个子领域？ → router + modules/ 结构
│ （SKILL.md 只做索引路由，每个子领域一个 module）
├── 多个独立情境集合？ → 拆分为多个 standalone skills
└── 单一深框架？ → 单 SKILL.md + 多层 reference/
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 180 lines · 113 tokens per session scan A 04ac6fdb5aee
distill-book is a skill published in the GitHub repository fanyty/claude-distill-book (5 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session and 1,979 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
pptx-import
A method for adding an uploaded PowerPoint presentation to an existing classroom as extra pages while keeping the slides' original layout. PowerPoint is Microsoft's presentation file format.
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
textbook-to-md
Convert PDF/EPUB textbooks to searchable markdown files for an AI agent's own reference. Use this skill whenever: (1) the user asks to convert a textbook/PDF chapter to markdown, (2) you need to search textbook content and no markdown version exists yet, (3) batch-converting a set of reference books into a knowledge…
scan-to-practice
A complete methodology for turning scanned or image-based learning materials into high-quality desktop, web, or mobile practice products. Covers visual transcription, data assembly, answer-key-driven controls and grading, product design, animation, validation, and long-term maintenance. Use when a user wants to…
svg-press
Teaches agents how to hand-craft self-contained SVG diagrams that render correctly in browsers, tags, and Playwright PDF/PNG. Covers containment math, viewBox sizing, arrow construction, text hierarchy, KDCube brand color tokens, semantic zone fills, badges, the PNG inspection loop, writepng parameters, multi-diagram…