Read, parse, and convert HWP/HWPX documents to Markdown or other formats.
npx skills add https://github.com/revfactory/skills --skill hwp
Please help me install this Agent Skill. Skill: hwp Source: https://github.com/revfactory/skills/tree/main/hwp Command: npx skills add https://github.com/revfactory/skills --skill hwp
HWP and HWPX documents are complex formats (binary and ZIP/XML) that require specialized tooling to extract text and tables, convert content, or generate new documents. This skill provides a cohesive, end-to-end capability for reading, parsing, and transforming Korean word-processor documents.
Use this skill to convert a provided HWP file to Markdown and extract its text.
High-intent search queries and answers about installing and using this skill.
HWP text extraction parses both binary OLE2/CFB structures and HWPX ZIP/XML packages to isolate and retrieve Korean document content. This process handles complex formatting to accurately extract readable text from Korean word-processor files.
HWP to Markdown conversion transforms parsed text, tables, and images from Korean word-processor documents into structured Markdown format. This enables seamless integration of HWP content into Markdown-based documentation workflows.
Generating HWPX from Markdown or plain text creates valid ZIP/XML structured documents. This allows you to programmatically produce Korean word-processor compatible files without needing the native application.
HWP is a binary format relying on OLE2/CFB structures, while HWPX uses a ZIP/XML package structure. Processing both requires specialized parsing logic to extract tables, images, and text accurately across these distinct document architectures.
Extracting tables and images from HWPX files involves parsing the internal ZIP/XML structure to locate and isolate embedded media and tabular data. This allows you to retrieve visual and structured grid content from Korean documents.
HWP document processing supports batch file workflows, allowing you to automate text extraction and Markdown conversion across multiple files. This streamlines large-scale document processing tasks for Korean word-processor formats.
seolcodingConvert HWP, HWPX, and HWPML files to Markdown or structured JSON.
itda-skillsConvert HWP and HWPX documents into Markdown or HTML.
tassiovaleConvert PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube URLs, and EPubs to Markdown.
cnhxExtract text, tables, and form data from PDF files into structured formats.
