hwp-pipeline

Convert HWP files to JSON, Markdown, HTML, or HWPX and replace placeholders.

16|9|Updated Apr 10, 2026
One-click install
npx skills add https://github.com/Yoojin-nam/hwp-pipeline --skill hwp-pipeline
Or copy as Structured Prompt for Agentโ–ผ
Please help me install this Agent Skill.
Skill: hwp-pipeline
Source: https://github.com/Yoojin-nam/hwp-pipeline/tree/main
Command: npx skills add https://github.com/Yoojin-nam/hwp-pipeline --skill hwp-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

๐Ÿ’ก This Skill requires python-hwpx, lxml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

It eliminates the difficulty of reading, converting, and editing Korean Hangul documents that are distributed as .hwp files by providing an end-to-end pipeline that works on any OS.

Core Features & Use Cases

  • Read HWP to useful formats: Convert .hwp into JSON, Markdown, or HTML so you can extract content without Hancom Office.
  • Convert HWP โ†’ edit-friendly HWPX: Transform .hwp into .hwpx using a Java-based converter, enabling downstream programmatic edits.
  • Edit/fill HWPX templates: Apply placeholder replacement (including in table cells) and normalize XML namespaces to produce filled documents.

Quick Start

Use the skill to fill placeholders in a Korean government form by converting the .hwp to .hwpx, replacing placeholders, and returning the filled output.

Frequently Asked Questions about hwp-pipeline

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

FAQPage Schema
How do I convert HWP to JSON or Markdown without Hancom Office?โ–ผ

You can convert HWP to JSON or Markdown without Hancom Office by using this pipeline to transform files and extract content directly. It reads .hwp files and outputs useful formats like JSON, Markdown, and HTML.

What's the best way to fill placeholders in HWPX templates programmatically?โ–ผ

Filling placeholders in HWPX templates programmatically is done by applying global ZIP-level replacement and optional namespace normalization. This process supports replacing placeholder text, including content located inside table cells.

Do I need Node.js and Java to convert HWP to HWPX for editing?โ–ผ

Yes, converting HWP to editable HWPX requires Node.js for reading HWP files and Java for the conversion process. Python 3 with python-hwpx and lxml is also needed for extraction and placeholder replacement.

Can I edit table cell content in HWPX files using python-hwpx?โ–ผ

Yes, you can edit table cell content in HWPX files using python-hwpx and lxml. The pipeline performs global ZIP-level replacement to update placeholders inside table cells and normalizes XML namespaces.

Does this HWP conversion pipeline work on any operating system?โ–ผ

Yes, this HWP conversion pipeline works on any operating system. It eliminates the difficulty of reading and editing Korean Hangul documents by providing an end-to-end pipeline independent of Hancom Office.

Why does my HWPX template replacement fail with XML namespace errors?โ–ผ

HWPX template replacement can fail with XML namespace errors if normalization is skipped. The pipeline includes optional namespace normalization to ensure global ZIP-level placeholder replacement processes XML structures correctly.