docx-cn

What This Skill Does

The docx-cn skill provides a robust framework for programmatically creating, manipulating, and analyzing Word documents (.docx files) within the OpenClaw ecosystem. At its core, the skill treats .docx files as structured ZIP archives containing XML. It facilitates text extraction, tracked change management, and the generation of highly specific document layouts. Whether you are generating complex reports with nested tables and images or parsing legacy documents, this skill acts as a bridge between high-level document automation and low-level XML manipulation.

Installation

You can install this skill directly via the command line or the OpenClaw package manager. Ensure you have the necessary dependencies such as LibreOffice for conversion tasks and Node.js for the docx-js library. Use the following command: clawhub install openclaw/skills/skills/guohongbin-git/docx-cn.

Use Cases

• Automated Reporting: Generate professional-grade business reports with custom headers, footers, and page sizes directly from JSON or database inputs.
• Document Conversion Pipeline: Convert legacy .doc files to modern .docx formats for standardization and automated analysis.
• Tracked Change Cleanup: Automate the process of accepting tracked changes in collaborative documents to finalize drafts before official distribution.
• Data Extraction: Extract and analyze content from large sets of documents for data processing workflows.

Example Prompts

1. "Create a new report in A4 size with a title header, a table of contents, and an image on the first page."
2. "Convert all legacy .doc files in the 'imports' folder to .docx format and extract the text content from each."
3. "Open the project_proposal.docx file and apply all tracked changes to generate a clean version for final review."

Tips & Limitations

• Page Sizing: Always explicitly define page dimensions in DXA units (1 inch = 1440 DXA) as the library defaults to A4; failing to do so may result in formatting drift for US Letter documents.
• Complexity Management: While document generation is straightforward, editing existing complex documents requires an understanding of the internal XML structure. Always use the validation script after modifying XML directly to avoid corrupting the document structure.
• Dependency Management: Ensure that LibreOffice is available in the environment path for successful file conversions and rendering images from documents. Performance may vary when handling exceptionally large files with high-resolution assets.