Book Distiller

炼金书:输入书名或电子书,自动深度调研→方法论提炼→生成该书的可运行框架Skill。 两种入口:(1)明确书名→直接蒸馏 (2)模糊学习需求→诊断荐书→再蒸馏。 触发词:「蒸馏这本书」「炼金XX」「把XX这本书做成skill」「XX的方法论skill」「更新XX的书skill」。 模糊需求也触发:「我想系统学谈判」「有没有一本书能帮我提升XX」。 English triggers: "distill [book]", "turn [book] into a skill", "book to framework skill". 不在用户只要书摘、读书笔记、买书推荐或查某个概念时触发——只在需要生成「可运行的方法论Skill」时激活。

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add AINoSleep/book-distiller-skill --skill book-distiller
Manual install
git clone --depth 1 https://github.com/AINoSleep/book-distiller-skill.git /tmp/book-distiller-skill
mkdir -p ~/.claude/skills
cp -r /tmp/book-distiller-skill/. ~/.claude/skills/book-distiller

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 炼金书 · 书籍蒸馏术

> 一本书值钱的从来不是它说了什么,是它让你在具体处境里知道该做什么。

## 核心理念

炼金书不做读书笔记,做**可运行的方法论**。

一个好的书籍Skill是这本书的"执行引擎":
- 书教了什么**核心方法**?(遇到X情况→做Y)
- 书给了什么**判断规则**?(怎么分辨该用哪个方法)
- 书里的**案例**证明了什么?(方法的边界在案例里)
- 这本书**在哪里失效**?(时代局限、领域边界、外部批评)
- 什么是蒸馏**做不到的**?(诚实边界)

**关键区分**:捕捉的是这本书让你 HOW to act,不是这本书 WHAT it says。摘要回答"书讲了啥",框架Skill回答"现在我该怎么办"。

---

## 执行流程

### Phase 0: 入口分流

| 用户输入 | 路径 | 示例 |
|---------|------|------|
| 明确书名 | **直接路径** → Phase 0A | 「蒸馏《影响力》」「把《高产出管理》做成skill」 |
| 模糊学习需求 | **诊断路径** → Phase 0B | 「我想系统学谈判」「有没有一本书能治我的拖延」 |

### Phase 0A: 需求澄清(直接路径)

收到明确书名后,确认(**每项都有默认值,确认不阻塞交付**):

1. **是哪本书**:书名+作者+版本(同名书、多版本书要确认;默认最新修订版)
2. **用途**:方法论顾问(默认)/ 执行清单 / 学习教练(费曼式带练)
3. **新建 or 更新**:检查 `.claude/skills/` 是否已有该书的Skill
4. **电子书语料**:「你手上有这本书的PDF/epub吗?有的话直接给我,蒸馏质量比纯网络调研高一个量级。没有也能做,走公开资料。」
5. **蒸馏档位**(开跑前必须报成本量级):

| 档位 | 调研规模 | 适用场景 | 成本量级 |
|------|---------|---------|---------|
| 快速 | 3个维度(骨架01+方法02+批评05),每维度限5个来源。案例索引从01/02顺带提取,产物中标注「快速档:案例颗粒度粗」 | 先试效果 / 薄书 / 预算敏感 | 约标准档1/3 |
| 标准(默认) | 6个维度完整调研 | 大多数场景 | 中等 |
| 深度 | 6维度 + 用户提供全书精读 + 领域后续研究追踪 | 打算开源发布的精品Skill | 最高 |

用户只说「就蒸这本」→ 默认:最新版 + 方法论顾问 + 无电子书 + 标准档,直接推进。

### Phase 0B: 需求诊断(模糊路径)

用户不知道该蒸哪本书,只有学习需求。通过≤2轮追问定位需求维度,然后推荐2-3本候选书。

| 需求维度 | 典型表达 | 候选书方向 |
|---------|---------|-----------|
| 说服与谈判 | 「总谈不下来」「不会拒绝」 | 影响力、掌控谈话、Never Split the Difference |
| 管理与组织 | 「带团队力不从心」 | 高产出管理、联盟、重来 |
| 决策与思维 | 「总是选错」「想不清楚」 | 思考快与慢、穷查理宝典、超越智商 |
| 写作与表达 | 「写不清楚」「没人看」 | 风格的要素、金字塔原理、On Writing Well |
| 习惯与执行 | 「坚持不下来」「拖延」 | 原子习惯、深度工作 |
Read the full skill on GitHub

Details

Skill name
book-distiller
License
MIT
Repo updated
17 August 2026

FAQ

What does the Book Distiller skill do?

炼金书:输入书名或电子书,自动深度调研→方法论提炼→生成该书的可运行框架Skill。 两种入口:(1)明确书名→直接蒸馏 (2)模糊学习需求→诊断荐书→再蒸馏。 触发词:「蒸馏这本书」「炼金XX」「把XX这本书做成skill」「XX的方法论skill」「更新XX的书skill」。 模糊需求也触发:「我想系统学谈判」「有没有一本书能帮我提升XX」。 English triggers: "distill [book]", "turn [book] into a skill", "book to framework skill". 不在用户只要书摘、读书笔记、买书推荐或查某个概念时触发——只在需要生成「可运行的方法论Skill」时激活。

How do I install the Book Distiller skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add AINoSleep/book-distiller-skill --skill book-distiller. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Book Distiller popular?

It lives in AINoSleep/book-distiller-skill, which has 5 GitHub stars and 0 forks.

Related skills

Camelot

5

Barinfo/Camelot.skill

No-mercy code review in the voice of Arthurian judgment. Code either proves itself worthy — like drawing the Sword from the Stone — or is rejected without sentiment. Evidence-bound findings, banishment-level severity grading (Exile/Dishonor/Counsel/Valour), and a final verdict at Camlann with actionable reforging orders. Use when the user asks for a harsh, expert code/PR review, or an evaluation of in-progress agent work. Stateless single-pass judge: it reviews whatever round of code it is handed; recursive round-robin is delegated to Ouroboros.

Software Development

Bambu 3mf

5

woolimi/bambu-3mf

코드로 만든 STL 부품을 Bambu Lab P2S 로 바로 뽑을 수 있는 Bambu Studio 프로젝트(.3mf)로 만든다. 부품마다 역할·하중·맞물림·환경을 정리한 부품 카드에서 재질(PLA·PETG·TPU·ABS·CF), plate, process preset, 부품별 설정(벽·infill·support·brim), 출력 방향, plate 배치를 Bambu Studio 번들 profile·Bambu Lab Wiki 근거로 정하고, Studio CLI 로 평탄화한 system profile 을 넣어 export → mesh·설정 검사 → plate 별 slice(시간·무게)까지 한 번에 돌린다. "3MF 만들어줘", "출력 파일 만들어줘", "Bambu Studio 프로젝트로", "바로 뽑을 수 있게", "슬라이스 설정 넣어줘", "필라멘트 뭐로 뽑아", "PETG 로 바꿔", "벽 늘려줘", "출력 시간 얼마나 걸려", "이 3MF 검토해줘", "설정 맞는지 봐줘", make_3mf·build_bambu_project 스크립트를 새로 만들거나 고칠 때, 이미 만든 3MF 를 검토할 때(scripts/review_3mf.py) 쓴다. 형상 정리·설계 뷰

Software Development

Codex Dispatch

5

yinguangyao/codex-dispatch-skill

Mandatory dispatch preflight before any subagent delegation. Use before the first child-work call in every task, and when starting Codex work that needs an explicit Direct vs Single/Parallel/Sequential choice: code edits, debugging, reviews, repo exploration, multi-file changes, ambiguous scope, high-risk judgment, or requests mentioning agents, delegation, parallel work, model choice, cost, token use, or over-delegation.

Software Development

Ask Codebuddy

5

zcx960/ask-codebuddy

Delegate self-contained subtasks to the locally installed CodeBuddy CLI — code analysis, review, approach comparison, and scoped edits. Use when work can be handed off to CodeBuddy to save context or use existing credits. 通过本机 CodeBuddy CLI 处理独立子任务。

Software Development

Ddd Architecture Coach

5

jed1978/ddd-architecture-coach

DDD Architecture Coach — a decision-making coach spanning DDD (Strategic + Tactical Patterns), AI/LLM engineering (intervention design, risk assessment, fallbacks), software engineering discipline (Clean/Hexagonal Architecture, testing, CI/CD, SBE), and cloud architecture (containers, serverless, observability, cost). Runs a four-phase architecture planning workflow (Phase 1 Domain Discovery / Phase 2 Architecture Design / Phase 3 Implementation Spec / Phase 4 Review & Iterate) and produces Context Maps, Aggregate designs, AI-ADRs, Key Examples (Gherkin), and decision records — NOT code. Suppo

Software Development

Ascend Operator Engineering

5

GTC2080/ascend-operator-skills

Design, implement, review, debug, and tune Huawei Ascend operators with Ascend C or TileLang Ascend. Use for TileLang environment setup, kernel semantics, tiling, UB/DMA/mask/synchronization, ACLNN or AOT integration, precision, MindStudio diagnostics, and trustworthy performance experiments; includes version-scoped lessons from DeepGEMM-Ascend and TileKernels.

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.