← 返回 Skills 市场
tanjinlimkelvin-dot

Book Deep Study

作者 tanjinlimkelvin-dot · GitHub ↗ · v3.1.1 · MIT-0
cross-platform ✓ 安全检测通过
138
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install book-deep-study
功能描述
把一本书、PDF、长文章或学习材料变成角色扮演式、对话式、分阶段的深度学习过程。用于用户想真正读懂、看透、吸收、内化一本书,而不是只要摘要的时候。触发场景包括:"陪我读这本书"、"帮我把这本书看透"、"像老师一样带我学"、"给我一个学习路径"、"一章一章带我读"、"和我对话式读这本书",或用户直接发来书名、PDF...
使用说明 (SKILL.md)

DEPRECATED

This is the old book-deep-study skill location.

Use the canonical skill instead:

  • /data/workspace/skills/skills/book-deep-study/SKILL.md

This file is intentionally kept minimal so older references do not silently use stale behavior.

安全使用建议
This skill is a prompt/template for stepwise, chapter-by-chapter study and appears internally consistent and low-risk. Before installing or using it, consider: (1) Any PDFs, screenshots, or book text you supply may contain sensitive or copyrighted material — avoid uploading private PII or content you don't want processed or retained in conversations. (2) Confirm which SKILL.md is active (the packaged SKILL.md is marked DEPRECATED and points to an absolute workspace path) so you know the exact runtime instructions the agent will follow. (3) Because it's instruction-only, the agent will rely on whatever system tools/permissions it already has to open or parse attachments; verify how your agent handles file attachments and whether those files are sent to any external services. If those checks look fine, the skill's behavior matches its description.
功能分析
Type: OpenClaw Skill Name: book-deep-study Version: 3.1.1 The skill bundle contains instructions and templates for an AI agent to act as a 'Chapter-by-Chapter Deep Study Teacher.' The content in 'references/chapter-by-chapter.md' and 'references/patterns.md' is entirely focused on educational guidance, structured book analysis, and checking user comprehension. There are no executable scripts, network calls, or instructions suggesting data exfiltration or unauthorized system access. The 'SKILL.md' file serves as a standard deprecation notice pointing to a canonical path, and no malicious intent or high-risk vulnerabilities were identified.
能力评估
Purpose & Capability
Name/description (deep, chapter-by-chapter study) align with the provided instruction documents — there are no unrelated env vars, binaries, or installs requested that would be unnecessary for the stated goal.
Instruction Scope
The SKILL is instruction-only and the reference files give detailed step-by-step prompts for processing books, PDFs, excerpts, and screenshots — all consistent with the stated purpose. The top-level SKILL.md is marked DEPRECATED and points to an absolute workspace path; this is a bookkeeping note rather than an operational instruction, but you may want to verify which canonical SKILL.md will be used at runtime.
Install Mechanism
No install spec and no code files — lowest-risk model for a skill that is purely prompt/instruction-based.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate to a prompt-driven reading/teaching assistant.
Persistence & Privilege
always is false and model invocation is allowed (the platform default). The skill does not request or attempt to modify other skills or system settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install book-deep-study
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /book-deep-study 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.1.1
- Marked the skill as DEPRECATED in SKILL.md. - Added clear instructions to use the canonical skill file instead. - Removed all previous documentation and guidance from SKILL.md. - Kept the file minimal to prevent usage of outdated information.
v3.1.0
Added: language matching (output in user's language), cross-chapter/cross-book connections, chapter jumping (no forced linear order), application layer requires explicit user confirmation, removed ambiguous Light Mode. Ultimate goal: user grasps ~80% of each chapter after deepdive.
v3.0.0
English version. Core: content-drive principle added — 9 tasks as checklist not template, allow skipping/merging, prevent formulaic output. Added judgment criterion: reader must feel the unique character of each chapter.
v2.0.0
Added content-drive principle: 9 tasks as checklist not template. Allow skipping/merging, prevent formulaic output. Added judgment criterion for quality.
元数据
Slug book-deep-study
版本 3.1.1
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 4
常见问题

Book Deep Study 是什么?

把一本书、PDF、长文章或学习材料变成角色扮演式、对话式、分阶段的深度学习过程。用于用户想真正读懂、看透、吸收、内化一本书,而不是只要摘要的时候。触发场景包括:"陪我读这本书"、"帮我把这本书看透"、"像老师一样带我学"、"给我一个学习路径"、"一章一章带我读"、"和我对话式读这本书",或用户直接发来书名、PDF... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 138 次。

如何安装 Book Deep Study?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install book-deep-study」即可一键安装,无需额外配置。

Book Deep Study 是免费的吗?

是的,Book Deep Study 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Book Deep Study 支持哪些平台?

Book Deep Study 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Book Deep Study?

由 tanjinlimkelvin-dot(@tanjinlimkelvin-dot)开发并维护,当前版本 v3.1.1。

💬 留言讨论