Convert PDF, Word, Excel, PowerPoint, and web pages to Markdown.
npx skills add https://github.com/hugohe3/hugo-skills --skill markdown-conversion
Please help me install this Agent Skill. Skill: markdown-conversion Source: https://github.com/hugohe3/hugo-skills/tree/main/skills/markdown-conversion Command: npx skills add https://github.com/hugohe3/hugo-skills --skill markdown-conversion
This Skill streamlines the process of converting a wide range of documents, including PDF, Word, Excel, PowerPoint, and web pages, into high-quality Markdown with embedded images, enabling seamless integration into various documentation workflows.
Use the markdown-conversion skill to convert a PDF document to Markdown, e.g. 'convert.py report.pdf'
High-intent search queries and answers about installing and using this skill.
You can convert PDF to Markdown by running the conversion script on your target file. The process utilizes PyMuPDF to extract text and embedded images, outputting a clean Markdown document for your workflows.
Yes, you can batch convert Word and Excel files to Markdown. The tool uses mammoth for Word and openpyxl for Excel, allowing you to process entire directories or multiple files at once into Markdown format.
The best way to convert web pages and HTML to Markdown is using this tool's built-in extraction libraries. It uses requests, beautifulsoup4, and trafilatura to fetch web URLs and transform HTML content into readable Markdown.
Yes, you need Python installed to run the conversion scripts. The tool relies on pandoc and various Python libraries like PyMuPDF and openpyxl to process different document formats into Markdown.
To extract images from PowerPoint during Markdown conversion, the tool uses python-pptx to process PPTX files. It can extract all images with full metadata or filter out decorative images based on your configuration.
Yes, you can convert EPUB and Jupyter Notebooks to Markdown for documentation. The tool applies ebooklib for EPUB files and nbconvert for Jupyter Notebooks, transforming their content into clean Markdown text.
ragnarokhaaExtract text from PDFs, scanned documents, and images using OCR.
zzafergokConvert Markdown documents to HTML using marked.js, pandoc, gomarkdown, or static site generators.
valalavSearch zolka.ru genealogical sections for surnames and retrieve matching snippets and links.
manuelbrandner85Extracts text, tables, and images from PDFs with OCR support.
