Convert PDFs and Office documents into structured Markdown with YAML frontmatter.
npx skills add https://github.com/notoriouslab/doc-cleaner --skill doc-cleaner
Please help me install this Agent Skill. Skill: doc-cleaner Source: https://github.com/notoriouslab/doc-cleaner/tree/main Command: npx skills add https://github.com/notoriouslab/doc-cleaner --skill doc-cleaner
Convert documents into clean, structured Markdown offline.
It applies to PDFs, Office formats, Keynote/Numbers, and more, preserving tables and enabling privacy-first, local processing. It uses PyMuPDF, python-docx, and pandas locally with optional AI backends, and outputs per-file Markdown with YAML frontmatter.
Install dependencies and run the CLI against your documents to generate Markdown outputs.
High-intent search queries and answers about installing and using this skill.
You can convert PDFs to clean Markdown offline using local libraries like PyMuPDF. This ensures privacy-first document processing by keeping all file data on your machine and outputs per-file Markdown with YAML frontmatter.
Yes, converting Office formats to Markdown preserves table structures during extraction. The tool uses python-docx and pandas locally to process files and retains table formatting within the structured Markdown output.
Local document processing supports Keynote and Numbers formats alongside PDFs and Office documents. It converts these formats into structured Markdown offline, maintaining privacy without requiring cloud uploads.
The best way to batch convert Office docs is running a local CLI against your documents. It processes each file into clean Markdown with YAML frontmatter using python-docx and pandas, generating organized outputs for every file.
You do not need an AI backend to convert documents to structured Markdown. The tool uses local libraries like PyMuPDF and python-docx by default, with AI backends being entirely optional for enhanced processing.
Offline document conversion outputs per-file Markdown to maintain clear source mapping and structured organization. Each document gets its own Markdown file with YAML frontmatter, making large batches of converted files easier to manage.
webdevtodayjasonExtract text from PDFs, scanned documents, and images using OCR.
lbliiiMigrates static site and Markdown content to Bengal format.
anilcan-karaExtract text from PDFs and scanned documents using pymupdf or marker-pdf.
tassiovaleExtract text and bounding boxes from PDFs, Office files, and images.
