Kordoc parse document
동해물과 백두산이 마르고 닳도록 대한민국 사정에 맞게 구성된 에이전트 스킬 모음.
npx -y skills add composite/korean-skills --skill kordoc-parse-documentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when converting Korean document files into readable text with `npx` and kordoc. Covers HWP, HWPX, and PDF parsing to Markdown or JSON, including metadata, outline, warnings, and page count. Trigger for requests such as reading a government document, extracting document contents, summarizing a Korean office file, or parsing a local .hwp/.hwpx/.pdf with `kordoc:parse_document`.
SKILL.md
1.9 KB, as published. Nobody here has run it
kordoc: parse_document
Use the public CLI first. This skill maps to the parse_document intent in src/mcp.ts, but without MCP.
Input Requirements
- Require exactly one target document.
- Require the user to attach the document or provide a concrete local path.
- Accept only supported formats:
.hwp,.hwpx,.pdf. - Do not proceed if the document is missing or the path is ambiguous.
Default Command
npm exec --yes --package=kordoc --package=pdfjs-dist -- \
kordoc /abs/path/document.hwpx
Use JSON when the caller needs blocks or metadata:
npm exec --yes --package=kordoc --package=pdfjs-dist -- \
kordoc /abs/path/document.hwpx --format json --silent
Workflow
- Resolve the target file to an absolute path.
- Confirm the extension is
.hwp,.hwpx, or.pdf. - Use plain CLI output for human reading.
- Use
--format jsonwhen the task needsmetadata,outline,warnings, orblocks. - Summarize the parsed content instead of dumping the whole document unless the user asked for raw output.
Guardrails
- Install
pdfjs-distalongsidekordoc; the package may fail to load without it. - Preserve warnings about image-based PDFs, skipped elements, or hidden text filtering.
- Do not claim OCR happened unless the execution path explicitly used an OCR-capable custom script.
- If the file is large, summarize key sections first.
- Refuse to continue when no supported document was provided.