oma-hwp

1# HWP Skill - HWP / HWPX / HWPML to Markdown Conversion
2 
3## Scheduling
4 
5### Goal
6Convert Korean HWP-family documents into readable Markdown or structured JSON while preserving document structure for LLM context, RAG, government-document review, or enterprise document processing.
7 
8### Intent signature
9- User asks to convert, parse, read, extract, or transform `.hwp`, `.hwpx`, or `.hwpml`.
10- User mentions Korean word processor files, Hangul documents, government forms, or "한글 파일".
11- User needs headings, tables, nested tables, lists, images, footnotes, or hyperlinks extracted from HWP-family files.
12 
13### When to use
14- Converting Korean HWP documents (`.hwp`, `.hwpx`, `.hwpml`) to Markdown
15- Preparing Korean government/enterprise documents for LLM context or RAG
16- Extracting structured content (tables, headings, lists, images) from HWP
17- User says "convert this HWP", "parse hwpx", "HWP to markdown", "한글 파일"
18 
19### When NOT to use
20- PDF files -> use `oma-pdf` (OCR + Tagged PDF specialization)
21- XLSX / DOCX files -> out of scope; run `bunx kordoc` directly if needed (note: `oma-docs` is the documentation-drift skill, not a converter)
22- Generating or editing HWP documents -> out of scope (kordoc itself supports `generate` / `fill` / `seal` / `patch` / `redact` / `lint` / `validate` / `render` subcommands; run `bunx kordoc@latest <subcommand>` directly if needed)
23- Already-text files -> use Read tool directly
24 
25### Expected inputs
26- `input_path`: `.hwp`, `.hwpx`, or `.hwpml` file path
27…