hwpx

Read, create, edit, and convert Korean HWP and HWPX documents.

Updated Feb 12, 2026
One-click install
npx skills add https://github.com/qmakescl/QSkills --skill hwpx-qmakescl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hwpx
Source: https://github.com/qmakescl/QSkills/tree/main/skills/hwpx
Command: npx skills add https://github.com/qmakescl/QSkills --skill hwpx-qmakescl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python-hwpx, pyhwp, lxml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Working with Korean Hangul (HWP/HWPX) files outside of Hancom Office is difficult because the formats are proprietary and most document libraries do not support them. This Skill lets an AI agent extract text, generate new documents, edit existing HWPX files, and convert between HWP, PDF, and DOCX formats. ## Core Features & Use Cases - Text Extraction: Extract text from both legacy binary .hwp files (via pyhwp) and modern XML-based .hwpx files (via python-hwpx TextExtractor), with LibreOffice as a fallback. - Document Creation & Editing: Generate new .hwpx documents with styled paragraphs (title, headings, body) and edit existing files through an unpack → XML edit → repack workflow, including table insertion via direct section0.xml manipulation. - Format Conversion: Convert HWP/HWPX files to PDF or DOCX using a LibreOffice headless wrapper. - Use Case: A Korean public institution employee receives a .hwp report and needs a PDF version plus an edited .hwpx with an added inventory table — the agent extracts, edits, and converts the files automatically. ## Quick Start Ask the agent to read the attached report.hwp file and convert it to a PDF document.

Frequently Asked Questions about hwpx

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

FAQPage Schema
How do I extract text from HWP files in Python?▼

Use pyhwp's hwp5txt module to parse legacy binary .hwp files, or python-hwpx's TextExtractor for XML-based .hwpx files. If pyhwp fails, LibreOffice headless conversion to txt works as a fallback.

How to convert HWP to PDF or DOCX on Linux?▼

Run LibreOffice in headless mode with the --convert-to flag, for example libreoffice --headless --convert-to pdf document.hwp. The soffice.py script wraps this command and outputs the converted file next to the original.

What is the difference between HWP and HWPX formats?▼

HWP is the legacy binary OLE Compound Document format, while HWPX is the newer XML-based format stored as a ZIP archive following the KS X 6101 standard. HWPX body content lives in Contents/section0.xml and can be edited directly.

Can I edit HWPX files without Hancom Office installed?▼

Yes. Unpack the .hwpx ZIP archive, edit Contents/section0.xml directly using lowercase hp: namespace tags, then repack the directory. The mimetype file must be stored uncompressed as the first ZIP entry.

Why does my edited HWPX file show a file corruption error?▼

Corruption errors occur when the hp:secPr element is missing from the first hp:p paragraph, when 2012 namespaces or uppercase tags are used, or when id attributes are duplicated. Keep the 2011 namespace declarations and unique random integer IDs.

Does pyhwpx work on Linux for HWP automation?▼

No, pyhwpx is Windows-only because it automates the Hancom Office COM interface. On Linux, use python-hwpx for .hwpx creation and reading, pyhwp for binary .hwp parsing, and LibreOffice for conversions.