Convert office documents into Markdown with optional OCR for scanned PDFs.
npx skills add https://github.com/ejoongseok/claude-settings --skill parse-doc
Please help me install this Agent Skill. Skill: parse-doc Source: https://github.com/ejoongseok/claude-settings/tree/main/claude-code/skills/parse-doc Command: npx skills add https://github.com/ejoongseok/claude-settings --skill parse-doc
This Skill removes the manual effort of converting scattered office documents into consistent, searchable Markdown, especially when files contain embedded text, tables, or scanned content.
Place your file in .local.claude/docs/original/ as meeting-notes.pdf, then run /parse-doc meeting-notes.pdf to generate .local.claude/docs/parsed/meeting-notes.md.
High-intent search queries and answers about installing and using this skill.
To convert scanned PDFs to Markdown, this tool automatically applies Tesseract OCR when standard text extraction returns empty, generating page-wise Markdown saved under the parsed output directory.
The best way to convert HWP and PPTX files to Markdown is using an automated parser that routes by file extension, utilizing kordoc for HWP and pptx2md for PPTX to produce searchable Markdown outputs.
Yes, you can batch convert DOCX and XLSX files by matching patterns like *.pdf, processing all matching files while skipping those already parsed in the output directory.
Yes, the document conversion tool extracts images from PDFs and PPTX files, leaving Markdown references so you can interpret the extracted images using multimodal reading capabilities.
You do not need Tesseract for legacy formats like ODT and ODS unless they are scanned images; Tesseract is an optional dependency used only when text extraction appears empty.
Your PDF to Markdown conversion may return empty if the file is scanned; the tool requires original input files in the correct directory and triggers OCR to handle image-based content.
mishahaninParse PDF, DOCX, PPTX, and XLSX files to extract text and spatial bounding boxes.
LogauaEngstromDetect scientific data file formats and generate Markdown EDA reports.
bailynloveExtract text from PDFs, scanned documents, and images using OCR.
caobingshengAutomate document creation, spreadsheet automation, and presentation generation across office formats.
