hwpx

Rewrite Hancom HWPX documents via XML-first reference-driven workflow.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/redasdm/Jeonbuk-AI-HWPX-Automation --skill hwpx-redasdm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hwpx
Source: https://github.com/redasdm/Jeonbuk-AI-HWPX-Automation/tree/main/hwpx
Command: npx skills add https://github.com/redasdm/Jeonbuk-AI-HWPX-Automation --skill hwpx-redasdm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lxml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of editing Hancom HWPX documents with high visual fidelity (styles, tables, cell merges, and page layout) without breaking the original structure.

Core Features & Use Cases

  • Reference-first XML preservation: Analyzes an attached .hwpx, extracts header.xml and section0.xml, then rewrites only the requested content while keeping structure and style IDs aligned.
  • XML-first generation/build pipeline: Creates or modifies HWPX by assembling templates and XML overrides, then validates the result.
  • Layout drift safety gate: Runs page_guard.py to block risky changes that would likely alter page counts, especially for reference-based edits.
  • Text extraction for understanding: Extracts plain text or Markdown (optionally including table/nested content) from a .hwpx.

Quick Start

Use the hwpx skill to generate an edited HWPX from an attached reference document and ensure the final page count matches the reference.

Frequently Asked Questions about hwpx

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

FAQPage Schema
How do I edit HWPX content without breaking the original page layout?

To edit HWPX content without breaking layout, use an XML-first workflow that rewrites text while preserving original structure and style IDs from header.xml and section0.xml. This ensures visual fidelity for styles, tables, and cell merges.

What is the best way to extract text from a Hancom HWPX document?

The best way to extract text from an HWPX document is using a reference-driven workflow that parses the OWPML XML structure, outputting plain text or Markdown while optionally capturing table and nested content.

How do I generate a new HWPX file from a template?

You generate a new HWPX file using an XML-first build pipeline that assembles templates and XML overrides, then validates the result to ensure OWPML integrity and well-formed XML.

Can I use Python and lxml to modify HWPX files?

Yes, you can use Python with lxml to modify HWPX files. lxml provides the XML parsing capabilities needed to analyze and rewrite OWPML structures while maintaining document validation.

Why does my HWPX page count change after editing?

Your HWPX page count changes because content edits altered the layout flow. A page guard mechanism blocks risky changes by enforcing page count matching between reference and output documents.