markdrop

Convert PDFs into structured Markdown and interactive HTML with AI descriptions.

210|18|Updated Dec 24, 2024
One-click install
npx skills add https://github.com/shoryasethia/markdrop --skill markdrop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markdrop
Source: https://github.com/shoryasethia/markdrop/tree/main
Command: npx skills add https://github.com/shoryasethia/markdrop --skill markdrop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Markdrop automates converting PDFs into structured Markdown and interactive HTML, while augmenting content with AI-driven descriptions for embedded images and tables to accelerate knowledge extraction.

Core Features & Use Cases

  • PDF to Markdown/HTML with preserved formatting and automatic image extraction.
  • AI-powered image and table descriptions across Gemini, OpenAI, Claude, Groq, OpenRouter, and LiteLLM.
  • Batch processing support and configurable prompts to tailor outputs for knowledge bases, reports, or training data.
  • Use Case: transform a folder of research papers into enriched Markdown suitable for ingestion into a document database.

Quick Start

Run markdrop convert on a PDF to generate Markdown and HTML, then run markdrop describe to enrich images and tables with AI descriptions.

Frequently Asked Questions about markdrop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert PDFs to Markdown with AI descriptions for images and tables?

Converting PDFs to Markdown with AI descriptions requires parsing the document structure and using a multi-provider AI backend to generate text for embedded images and tables. Markdrop automates this extraction and enrichment process.

Can I batch process PDF to HTML conversions with configurable AI prompts?

Batch processing PDF to HTML conversions is supported alongside configurable AI prompts. This allows you to tailor the output descriptions for knowledge bases, reports, or training data across a folder of research papers.

Does markdrop support multiple AI providers for generating image descriptions?

Multiple AI providers are supported for generating image descriptions, including Gemini, OpenAI, Claude, Groq, OpenRouter, and LiteLLM. This multi-provider backend offers flexible model overrides for real-world document workflows.

What Python version is required to convert PDFs to structured Markdown?

Python 3.10 or higher is required to convert PDFs to structured Markdown using this tool. The environment also relies on repository dependencies and includes built-in SSRF and path-traversal protections for secure processing.

What is the best way to transform a folder of research papers into enriched Markdown?

Transforming a folder of research papers into enriched Markdown is best handled by running automated batch processing. This extracts text and images, then uses AI-assisted descriptions to make the output suitable for document database ingestion.

Are there built-in protections when extracting images from PDFs to HTML?

Built-in SSRF and path-traversal protections are included when extracting images from PDFs to HTML. These security measures ensure safe processing of real-world document workflows without exposing the system to common vulnerabilities.