Word and WPS Batch Markdown Converter
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md and install @user_f474679a/tomark-skill.
About this skill
The Problem
In Windows workflows, .docx, .doc, and .wps files do not cleanly become Markdown by default. .docx conversion can rely on mammoth to preserve headings, bold text, and lists, while .doc and .wps files need WPS Office to convert them to .docx first. Batch runs also need to preserve sub-directory structure and make it easy to audit which files succeeded or failed.
How It Works
tomark-skill centers on scripts/convert_to_markdown.py:
- Single or batch conversion: set SRC_DIR, optionally OUT_DIR, with default output under /markdown_output/
- Format routing: .docx uses mammoth; .doc / .wps use KWps.Application COM to produce .docx first
- Auditable results: Markdown files are emitted and 转换报告.md lists successes and failures
- Stable encoding: UTF-8 runtime mode is recommended, the script forces UTF-8 stdout, and output files are written as UTF-8
Boundaries
This skill targets Windows office-document conversion. If WPS Office is unavailable, .doc and .wps files cannot be converted, and only .docx files can be processed. Password-protected or severely corrupted documents may fail. It focuses on conversion and batch output, not perfect reconstruction of complex tables, formulas, or visual layout.
Use Cases
- Maintain a Windows document library and batch-export nested .docx files to Markdown.
- Convert legacy .doc or .wps files via WPS to .docx before exporting Markdown.
- Use the generated conversion report to identify failures from protected or corrupted files.
- Organize office materials in subdirectories and keep the same folder hierarchy in .md output.
Best For
- Windows documentation engineers maintaining office archives who need stable UTF-8 Markdown output.
- Editors organizing legacy Word or WPS materials who need batch conversion with headings, bold, and lists.
- Team assistants handling nested document folders who want .md output to mirror the source hierarchy.
- Operations engineers troubleshooting batch failures who need a report to locate problematic files.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Turn a topic, notes, or tables into a complete PPT plan with logic, page layouts, visual and chart guidance, and natural defense scripts.