Markdrop provides a Python API and CLI to convert PDF documents into structured Markdown and interactive HTML, extract images and tables, and use AI vision models to generate contextual descriptions for extracted content. It supports batch processing and multiple LLM backends (Gemini, OpenAI, Anthropic, Groq, OpenRouter, LiteLLM).
Use Markdrop when you need to turn reports, papers, or PDFs into reusable Markdown/HTML with rich, AI-generated captions for images and tables — for documentation, publishing, or data extraction workflows. It’s appropriate for single-file conversions or large batch jobs.
Likely compatible with agents that can run Python and shell commands and invoke external LLMs (Copilot/Codex-style code agents, CLI-capable agents).
Markdrop is a Python tool for converting PDFs to structured Markdown/HTML with AI-powered image and table descriptions using multiple LLM providers. No bundled scripts were present for testing. The SKILL.md is well-documented with clear Python API and CLI examples, though it lacks error handling guidance and troubleshooting tips.
Clean skill with no security concerns. Well-written documentation covering both CLI and Python API. Architecture is simple (single SKILL.md, no scripts or references). Could improve with error handling examples, troubleshooting section, and better separation of concerns.
