HWPX Document Toolkit

What it does

This skill provides a full pipeline for working with HWP/HWPX (Hancom Office) documents: convert legacy .hwp binaries to HWPX, generate HWPX from markdown/text/URLs, clone and fill complex templates, and validate/fix namespace issues so generated files open correctly. It includes build and verification scripts, template assets, and detailed rules for government document formatting.

When to use it

Use when you need reliable HWPX outputs (reports, proposals, official documents) or must convert .hwp files into editable HWPX for downstream processing. It's essential for workflows requiring template preservation (tables, images, styles) and for generating documents that must follow strict public-sector formatting rules.

What's included

• Scripts: convert_hwp.py, build_hwpx.py, fix_namespaces.py, validate.py, clone_form.py, verify_hwpx.py, text_extract.py, md2hwpx.py and helper library hwpx_helpers.py
• References: XML structure, template-style mappings, troubleshooting and public-sector writing rules (2025)
• Instructions: decision tree for workflows A–H, CLI examples for conversion, cloning, building, and verification; strict rules for namespace postprocessing and validation

Compatible agents

Designed for agents or runtimes that can run Python tooling and shell commands; especially useful where document fidelity (tables/images/styles) is critical, such as Korean government or enterprise document pipelines.