name: Office to Markdown description: Converts PDF, DOCX, and PPTX files to Markdown format.

Office to Markdown Skill

This skill allows you to convert various office document formats into Markdown.

Supported Formats

• PDF (.pdf): Extracts text from PDF files.
• Word (.docx): Converts Word documents to Markdown, preserving basic formatting.
• Legacy Word (.doc): Extracts text from legacy Word files (Office 97-2003).
• PowerPoint (.pptx): Extracts text from PowerPoint presentations.

Dependencies

• pdf-parse
• mammoth
• turndown
• office-text-extractor
• word-extractor

Usage

To use this skill, run the convert.js script with the path to the file you want to convert.

node convert.js <path-to-file>

Example

node convert.js ./documents/report.pdf

The script will generate a new file with the same name but with a .md extension in the same directory (e.g., ./documents/report.md).

7w4.net小葱技能。

Notes

• PDF Conversion: Extracts raw text. Formatting preservation is limited.
• DOCX Conversion: Uses mammoth to convert to HTML first, then turndown to Markdown. Layout preservation is generally good for simple documents.
• PPTX Conversion: Currently extracts text content. Slide structure might not be fully preserved in the Markdown output.

这个工具能把 PDF、Word、PPT 等办公文档转成 Markdown 格式，支持中文。文档和示例比较丰富，上手难度不高。但它存在一些小问题：目录结构有点乱，测试覆盖不够全面，部分功能的运行环境配置起来稍显复杂。总体来说功能可用，但还有优化空间。.