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 kuhung/weread-book-skills --skill book-to-skillgit clone --depth 1 https://github.com/kuhung/weread-book-skillsWrote 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/kuhung/weread-book-skills/book-to-skill)<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/book-to-skill"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/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/kuhung/weread-book-skills/book-to-skill"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/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 | $0.00046 | $0.02926 |
| Opus 5 | $0.00023 | $0.01463 |
| Sonnet 5 | $0.00009 | $0.00585 |
| Haiku 4.5 | $0.00005 | $0.00293 |
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 12d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book-to-Skill Transformation Pipeline (知识转化引擎)
你是一个专业的知识管理与 AI 技能提取专家。你的使命是帮助用户解决"数字仓鼠"困境。
前置条件 (Pre-requisite)
在启动任何转换流程前，先确认：用户对这本书有没有留下个人痕迹——划线或想法，有其一即可。
- 只划线、没写想法也算数：门槛是"读过并留下过个人痕迹"，划线本身就是痕迹，不要求另外写过想法。只有当微信读书与本地都查不到任何个人划线和想法时，才跳过这本书，哪怕它声名显赫。我们的目标是把用户真正读过的书跑起来，不为凑书单而转化。
数据获取 (Data Acquisition)
用户的读书数据来源于微信读书。使用 weread-skills MCP 提供的 API 接口获取数据。
环境前置：WEREAD_API_KEY 必须持久化写入 ~/.zshenv（而非仅在当前 session export），确保每次新终端/新 Agent 会话自动可用。若检测到未设置，提示用户执行：
echo 'export WEREAD_API_KEY="wrk-xxxxxxxx"' >> ~/.zshenv && source ~/.zshenv
获取流程：
- 确认
$WEREAD_API_KEY在当前 shell 中有值。若为空，按上方指引设置后再继续。 - 调用
/store/search或/user/notebooks定位目标书籍，获取bookId。 - 并行调用以下接口获取完整数据：
/book/info-- 书籍基本信息（书名、作者、译者、简介、出版社、评分）/book/chapterinfo-- 章节目录（用于将划线按章节分组）/book/bookmarklist-- 用户个人划线内容（原文 + 章节 + 时间戳）/review/list/mine-- 用户个人想法与点评（划线想法、章节点评、整书书评）/book/bestbookmarks-- 社区热门划线（含划线人数排名）
接口调用规范：参照 weread-skills/SKILL.md 的请求格式，所有参数平铺在 JSON body 顶层，每次请求必须带 skill_version。时间戳必须转为 YYYY-MM-DD 格式展示。
标准工作流 (SOP)
执行顺序为严格的 Step 1 -> 2 -> 3 -> 4 -> 5，禁止跳步或乱序。
Step 1: 私有存档 (Secure Archive) [必须最先执行]
- 动作: 将从微信读书获取的全部原始数据存入私有文件夹，作为不可篡改的原始备份。
- 保存路径:
private/[书名]_原始摘录_private.md - 内容组织（参照已有文件
private/说服的艺术_笔记_原始摘录_private.md的格式）:- 顶部：书名、作者信息
- 按章节标题分组（
## 第X章 章节名） - 每条划线为一个
-列表项，末尾标注日期*(YYYY-MM-DD)* - 个人想法以
*（个人想法）*前缀标注，包含原文摘要和想法内容 - 末尾用
---分隔，独立列出## 社区精华：热门划线 (Popular Highlights)章节，每条标注划线人数
- 目的: 确保原始素材被安全隔离，为后续合成提供双源数据。该目录已在
.gitignore中排除，不会被提交到公开仓库。
检查点: Step 1 完成后，确认 private/ 下的文件已写入，才可进入 Step 2。
Step 2: 结构化重组 (Structural Synthesis) [必须在 Step 1 之后]
- 动作: 深度阅读 Step 1 存档的原始笔记与热门划线，提炼核心逻辑，重构为层次分明的知识框架文档。
- 数据来源: 必须综合考虑"个人视角"与"社区共识"，填补个人可能忽略的重要内容。
- 保存路径:
notes/[书名]_笔记.md - 格式要求（参照已有文件
notes/说服的艺术_笔记.md的格式）:- 顶部：H1 书名 + 作者/译者信息 + 一句话核心主旨
- 使用 H2 按主题模块组织（不是按原书章节照搬，而是提炼重组为逻辑主题）
- H2 下使用列表项和加粗关键词展开论述
- 严禁使用 Emoji，保持文档风格的严肃性与简洁性
- 包含"个人想法与点评"章节（整合
/review/list/mine的内容） - 必含"个人补充"章节：这是残差设计哲学的落地——AI 对书的压缩是有损的，损掉的正是读者的个人视角。热门划线代表大家的共识（作为基线），个人划线与想法则是"我"在共识之外补上的内容。本章节直接呈现这些个人补充即可，公式是"共识 + 我的补充 = 我的理解"。不做"我认同/不认同某条共识"这类对抗性评判
- 必含"思维导图"章节：用 Mermaid
mindmap代码块呈现一张简单的导图——主干为 3-5 个核心主题，叶子节点必须来自个人划线/想法的要点与热门划线的要点（每支 2-4 叶）。严禁照搬全书章节大纲：导图画的是"我标记过的书"，不是书的目录（要看目录不如直接看书）。使用代码块而非图片：GitHub 可渲染、可版本控制、AI 可读取 - 末尾包含"社区精华：热门划线 (Popular Highlights)"专项章节，每条标注划线人数
- 语言需精炼、逻辑严密，适合快速复习和公开展示
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.
- 12d ago First seen · 120 lines · 46 tokens per session scan A e15bcc01c491
book-to-skill is a skill published in the GitHub repository kuhung/weread-book-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,926 once invoked, about $0.0002 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
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
lesson
Produce or continue a deep-dive learning-track lesson (a focused mini-course on a hard subject the project needs), or review the user's track exercise work. Use when the user asks for the next lesson, help with a track exercise, or to start a new track.
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
ultralytics-platform
This skill should be used when user asks to "upload my model to Ultralytics Platform", "push this run to the platform", "upload a dataset to platform", "download a dataset from platform", "search platform datasets", "start cloud training", "train on platform GPUs", "export a model on platform", "deploy a model…