Reading Digest — Document Summarization & Reading Notes

When to Use

• User wants a summary of a long Yuque document
• User says "帮我总结这篇文档", "summarize this doc", "生成阅读摘要"
• User wants to extract key points from an article for future reference
• User says "这篇文章讲了什么", "帮我提炼要点"

Required MCP Tools

yuque-mcp

• yuque_search

  — Find the target document by keyword

• yuque_get_doc

  — Read the full document content

• yuque_list_repos

  — List personal repos to find the save target

• yuque_create_doc

  — Save the reading digest as a new document

Workflow

Step 1: Locate the Document

• A document title or keyword
• A direct Yuque document URL
• A repo + doc reference

Tool: yuque_search
Parameters:
  query: "<keyword>"
  type: "doc"

repo_id

doc_id

Step 2: Read the Document

Tool: yuque_get_doc
Parameters:
  repo_id: "<namespace>"
  doc_id: "<slug>"

Step 3: Generate the Reading Digest

# 📖 阅读摘要：[文档标题]

> **原文**：[文档标题](文档链接)
> **作者**：[作者]
> **阅读日期**：YYYY-MM-DD
> **预计阅读时间**：约 X 分钟

---

## 🎯 一句话总结

[用一句话概括文档的核心观点或目的]

---

## 📌 关键要点

1. **[要点 1]**：[简要说明]
2. **[要点 2]**：[简要说明]
3. **[要点 3]**：[简要说明]
4. **[要点 4]**：[简要说明]
5. **[要点 5]**：[简要说明]

---

## 🧠 核心论点与逻辑

[梳理文档的核心论证逻辑，2-3 段]

---

## 💡 启发与思考

- [这篇文档对我的启发 1]
- [这篇文档对我的启发 2]
- [可以应用到的场景]

---

## 📝 原文金句

> [摘录文档中值得记住的精彩段落 1]

> [摘录文档中值得记住的精彩段落 2]

---

## 🔗 相关延伸

- [可以进一步阅读的方向 1]
- [可以进一步阅读的方向 2]

---

> 本摘要由 AI 助手生成，建议结合原文阅读。

Step 4: Review with User

• "摘要是否准确？有需要调整的地方吗？"
• "要保存到你的语雀知识库吗？"

Step 5: (Optional) Save to Yuque

Tool: yuque_list_repos
Parameters:
  type: "user"

Tool: yuque_create_doc
Parameters:
  repo_id: "<namespace>"
  title: "📖 阅读摘要：[原文标题]"
  body: "<formatted digest>"
  format: "markdown"

Step 6: Confirm

✅ 阅读摘要已生成并保存！

📄 **[📖 阅读摘要：原文标题](文档链接)**
📚 已归档到：「知识库名称」

### 摘要概览
- 提炼了 X 个关键要点
- 摘录了 X 条原文金句
- 生成了 X 个延伸阅读方向

Guidelines

• Preserve the author's original intent — don't distort or over-simplify
• Key points should be specific and actionable, not vague generalizations
• Include direct quotes from the original for important claims
• The "启发与思考" section should be personalized — relate to the user's context if known
• Default language is Chinese; match the original document's language
• For very long documents (>5000 words), consider breaking the digest into sections matching the original structure

Error Handling

yuque_search

yuque_get_doc

yuque_get_doc