Kimi Docx

This one generates and edits Word documents through direct XML manipulation rather than typical libraries like python-docx. It uses C# for creating new docs and Python for editing existing ones, which is an unusual split but apparently intentional for quality. The source material is thorough about formatting preservation, includes templates for covers and charts, and has strong opinions about professional touches like headers, footers, and table of contents. If you need to programmatically create polished Word documents with actual visual design rather than just dumping content into default styles, this handles that. The mandatory validation pipeline and pandoc verification suggest the author has been burned by invisible corruption before.

skills.sh installs: 509
GitHub stars: 245
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add thvroyal/kimi-skills --skill kimi-docx --agent claude-code

Installs into .claude/skills of the current project.

Files

Part 1: Goals

⚠️ When to Unzip vs Read

To preserve ANY formatting from the source document, MUST unzip and parse XML.

Read tool returns plain text only — fonts, colors, alignment, borders, styles are lost.

Need	Method
Text content only (summarize, analyze, translate)	Read tool is fine
Formatting info (copy styles, preserve layout, template filling)	Unzip and parse XML
Structure + comments/track changes	`pandoc input.docx -t markdown`

Core Principles

Preserve formatting — When editing existing documents, retain original formatting. Clone and modify, never recreate.
Correct feature implementation — Comments need multi-file sync. Track Changes need revision marks. Use the right structure.

Never use python-docx/docx-js as fallback. These libraries produce lower quality output than direct XML manipulation.