doc_to_md_agent

Convert local documents to Markdown via CLI, FastAPI, or Python workflows.

Updated Nov 8, 2025
One-click install
npx skills add https://github.com/ferryhe/doc_to_md --skill doc-to-md-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: doc_to_md_agent
Source: https://github.com/ferryhe/doc_to_md/tree/main/skills/doc_to_md_agent
Command: npx skills add https://github.com/ferryhe/doc_to_md --skill doc-to-md-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Convert local documents into Markdown-ready content and orchestrate the appropriate CLI/API workflows, including routing PDF OCR across opendataloader, mistral, and mathpix for prose, printed formulas, or handwritten formulas.

Core Features & Use Cases

  • CLI, API, and in-process Python interfaces to drive conversions
  • Engine readiness checks and guided engine selection for prose vs formulas
  • Quality assessment guidance with per-document metrics and tracing
  • Support for formula-intensive PDFs with engine-specific paths

Quick Start

Convert a local document to Markdown via CLI or API and evaluate the resulting quality.

Frequently Asked Questions about doc_to_md_agent

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

FAQPage Schema
How do I convert a local PDF with mathematical formulas to Markdown?

You can convert formula-heavy PDFs to Markdown by routing OCR through engines like mathpix, mistral, or opendataloader. The tool implements engine-specific paths to handle printed or handwritten formulas and assesses per-document quality metrics.

Can I batch convert multiple documents to Markdown via an API?

Yes, batch converting documents to Markdown is supported through CLI, FastAPI, and in-process Python workflows. The tool orchestrates these interfaces for both single-document and batch conversion tasks, providing per-document quality metrics and tracing outputs.

What is the best way to evaluate the quality of a Markdown conversion?

Evaluating Markdown conversion quality is handled through built-in per-document metrics and tracing. The tool provides quality assessment guidance to help verify engine readiness and check the accuracy of converted prose and formula-heavy content.

Does this document to Markdown converter support CLI workflows?

Yes, the document to Markdown converter supports CLI workflows alongside FastAPI and in-process Python interfaces. It includes engine readiness checks and guided engine selection to help you choose the right OCR path for your files.

How do I choose the right OCR engine for converting prose versus formulas?

Choosing the right OCR engine for converting prose versus formulas is guided by built-in engine readiness checks. The tool routes PDF OCR across opendataloader, mistral, and mathpix based on whether your content is prose, printed formulas, or handwritten formulas.

When do I need engine readiness checks for Markdown conversion?

Engine readiness checks for Markdown conversion are needed when routing content to specific OCR engines like mathpix or mistral. These checks verify that the selected engine is available and properly configured for processing your prose or formula-heavy PDFs.