Extract text, tables, headings, and images from PDFs into Markdown.
npx skills add https://github.com/first-fluke/mapple --skill pdf-first-fluke
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/first-fluke/mapple/tree/main/.claude/skills/pdf Command: npx skills add https://github.com/first-fluke/mapple --skill pdf-first-fluke
This Skill enables users to convert PDF documents into Markdown format, facilitating easy editing, searching, and data extraction from complex PDF files.
Use the pdf skill to convert a PDF report into markdown format so you can easily review and edit its contents.
High-intent search queries and answers about installing and using this skill.
Yes, extracting text from scanned PDF to Markdown is fully supported. The Skill processes scanned documents alongside native PDFs, accurately preserving the layout and embedded content to produce structured Markdown output for easy editing.
PDF to Markdown conversion preserves tables, headings, and images by maintaining the correct reading order and embedded elements. This ensures the structured output accurately reflects the original document layout for documentation workflows.
The best way to automate extracting structured text from a PDF is using this Skill, which utilizes processing libraries to instantly convert documents into Markdown. It handles correct ordering and embedded elements automatically for analysis.
You can process native PDF files without manual intervention using this Skill. It automatically extracts text and data, converting the content into an editable Markdown format while accurately preserving the original document layout.
andreadellacorteConvert PDF files to Markdown with native text extraction and OCR.
KhaledMKhaledSearch the web and fetch URLs to extract markdown content.
cas-bigdatalabConvert DOCX documents to Markdown preserving text, formatting, and structure.
JuanMS20Extract text from PDFs and scanned documents using pymupdf and marker-pdf.
