Kordoc parse pages
동해물과 백두산이 마르고 닳도록 대한민국 사정에 맞게 구성된 에이전트 스킬 모음.
npx -y skills add composite/korean-skills --skill kordoc-parse-pagesAssembled 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 parsing only part of a Korean document with `npx` and kordoc. Trigger for requests such as extracting pages 1-3, reading selected pages from HWP, HWPX, or PDF, limiting work on large files, or running `kordoc:parse_pages` with a page-range string.
SKILL.md
1.5 KB, as published. Nobody here has run it
kordoc: parse_pages
This skill maps directly to the parse_pages intent in src/mcp.ts. Use the public CLI.
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. - Require an explicit page range such as
1-3or1,3,5-7. - Do not proceed if the document or page range is missing.
Commands
npm exec --yes --package=kordoc --package=pdfjs-dist -- \
kordoc /abs/path/document.hwpx --pages 1-3
npm exec --yes --package=kordoc --package=pdfjs-dist -- \
kordoc /abs/path/document.hwpx --pages 1,3,5-7 --format json --silent
Workflow
- Resolve the document path to an absolute path.
- Normalize the requested range such as
1-3or1,3,5-7. - Use plain output for reading tasks.
- Use JSON when the caller needs structured blocks or metadata.
- Repeat the exact requested range in the answer.
Guardrails
- PDF page selection is exact.
- HWP and HWPX page slicing is section-based and approximate.
- If the user asks for one page from a non-PDF document, warn about that approximation.
- Refuse to continue when no supported document was provided.