메뉴
Use when extracting document metadata with `npx` and kordoc instead of reading the full document text. Trigger for requests about title, author, created date, or quick inspection of local HWP, HWPX, and PDF files through `kordoc:parse_metadata`.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when diffing two Korean documents with `npx` and kordoc. Covers HWP, HWPX, and cross-format comparisons for requests such as 신구대조표 preparation, change review between document versions, block-level additions and removals, or invoking `kordoc:compare_documents` on two local files.
Use when identifying whether a Korean document file is HWP, HWPX, PDF, or unknown with `npx` and kordoc. Trigger for triage requests such as checking file type before parsing, validating uploads, routing mixed office files, or using `kordoc:detect_format` on local documents.
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`.
Use when extracting structured label-value fields from Korean forms with `npx` and kordoc. Trigger for requests involving applications, government forms, personnel sheets, contact fields, or any HWP, HWPX, or PDF document that should be processed with `kordoc:parse_form`.
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.
Use when extracting a specific table from a Korean document with `npx` and kordoc. Trigger for requests such as pulling the first or Nth table from HWP, HWPX, or PDF, isolating tabular content for review, or using `kordoc:parse_table` with a zero-based table index.
| name | kordoc-parse-metadata |
| description | Use when extracting document metadata with `npx` and kordoc instead of reading the full document text. Trigger for requests about title, author, created date, or quick inspection of local HWP, HWPX, and PDF files through `kordoc:parse_metadata`. |
src/mcp.ts uses internal metadata-only helpers, but the public npx kordoc surface does not expose that fast path. With npx only, emulate the tool by parsing JSON and returning just the metadata fields.
.hwp, .hwpx, .pdf.npm exec --yes --package=kordoc --package=pdfjs-dist -- node <<'SCRIPT'
const p = require("path"), fs = require("fs");
const nmBin = process.env.PATH.split(p.delimiter).find(d => d.endsWith(".bin"));
const kUrl = "file:///" + p.join(p.resolve(nmBin, ".."), "kordoc", "dist", "index.js").split(p.sep).join("/");
import(kUrl).then(async (k) => {
const filePath = "/abs/path/document.hwpx";
const raw = fs.readFileSync(filePath);
const buffer = raw.buffer.slice(raw.byteOffset, raw.byteOffset + raw.byteLength);
const result = await k.parse(buffer);
if (!result.success) throw new Error(result.error);
console.log(JSON.stringify({
fileType: result.fileType ?? null,
pageCount: result.pageCount ?? null,
metadata: result.metadata ?? null,
outline: result.outline ?? null,
warnings: result.warnings ?? null
}, null, 2));
}).catch(e => { console.error(e); process.exit(1); });
SCRIPT
npx-only.