doc-mindmap

Convert office documents to Markdown and generate local summaries with Ollama.

27|6|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/crazynomad/skills --skill doc-mindmap
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc-mindmap
Source: https://github.com/crazynomad/skills/tree/main/doc-mindmap
Command: npx skills add https://github.com/crazynomad/skills --skill doc-mindmap

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown, requests, and includes scripts (resource) components.

What problem does it solve?

散落的办公文档(PDF、PPT、Word、Excel 等)需要批量整理、转换为可阅读的结构化文本,并在本地模型上生成摘要与分类。本 Skill 提供完整的端到端工作流,降低手动重复劳动。

Core Features & Use Cases

  • Batch conversion: 将 PDF、PPT、Word、Excel 等文档批量转换为 Markdown,便于搜索与整理。
  • Local summaries: 使用 Ollama 本地模型生成简明摘要,不依赖外部服务。
  • Three-dimensional classification: 按主题/用途/客户对文档进行多维分类,并提供命名建议。
  • Soft-link organization: 通过软链接输出多种分类视图,零额外磁盘占用。
  • Indexing & deduplication: 生成 CSV 索引并检测重复文件,帮助清理磁盘。

Quick Start

将一个文件夹中的办公文档批量转换为 Markdown,并在本地模型上生成摘要、完成三维分类并输出软链接结构。

Frequently Asked Questions about doc-mindmap

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch convert office documents like PDF, Word, and Excel to Markdown?

Batch converting office documents to Markdown relies on markitdown to parse PDF, PPT, Word, and Excel files, outputting structured Markdown text for easy search and organization.

Can I generate summaries for large document repositories using a local model?

Generating local summaries for large document repositories utilizes the Ollama local model, creating concise briefs without relying on external cloud services.

What is three-dimensional document classification and how does soft-link organization work?

Three-dimensional document classification categorizes files by topic, usage, and client, while soft-link organization outputs classification views via directory links with zero extra disk space.

Do I need Python and Ollama to automatically summarize and classify office files?

Automated summarization and classification of office files requires Python 3.10+ and a local Ollama setup, alongside dependencies like markitdown and requests for processing.

How do I index converted Markdown files and detect duplicate documents on disk?

Indexing converted Markdown files and detecting duplicates generates a CSV index and checks redundant files, helping clean disk space and manage document repositories.