HWP to Markdown Converter
Converts Korean Hangul Word Processor (HWP/HWPX) documents into structured Markdown or JSON for LLM context and data processing.
This skill enables Claude to seamlessly parse and transform legacy and modern Korean Word Processor files (HWP, HWPX, HWPML) into clean, structured Markdown. By leveraging the kordoc engine, it extracts complex elements like nested tables, images, and footnotes while performing essential post-processing like table flattening and Private Use Area (PUA) glyph removal. It is an essential tool for developers and data scientists working with Korean government documents, enterprise archives, or building RAG (Retrieval-Augmented Generation) pipelines that require high-fidelity Korean text extraction.
주요 기능
01Supports HWP, HWPX, and HWPML format conversion
02Cleans Private Use Area (PUA) glyphs for better font compatibility
03Flattens merged cells for GitHub Flavored Markdown (GFM) compatibility
04Supports batch processing and specific page range extraction
051,077 GitHub stars
06Extracts complex tables, headings, lists, images, and footnotes
사용 사례
01Extracting structured data from complex Hancom Office tables for data analysis
02Preparing Korean government and enterprise documents for AI-ready RAG pipelines
03Converting legacy HWP archives into searchable, web-friendly Markdown documentation