skills.rest
FuZhiyu
FuZhiyuCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

mistral-pdf-to-markdown

Convert PDF documents into structured Markdown with extracted images using Mistral OCR.

8|2|Updated Apr 9, 2026
Search Tags:#ocr#pdf#research papers#markdown conversion#image extraction#mistral#scanned documents
One-click install
npx skills add https://github.com/FuZhiyu/superRA --skill mistral-pdf-to-markdown
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mistral-pdf-to-markdown
Source: https://github.com/FuZhiyu/superRA/tree/main/skills/mistral-pdf-to-markdown
Command: npx skills add https://github.com/FuZhiyu/superRA --skill mistral-pdf-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mistralai, pypdf, python-dotenv, pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the manual effort of transcribing scanned or complex-layout PDFs by converting them into structured Markdown while preserving document organization and extracting embedded images.

Core Features & Use Cases

  • Mistral OCR Conversion: Convert scanned, image-based, and complex-layout PDFs into readable Markdown through Mistral's OCR API.
  • Image Extraction: Save embedded document images in a conversion-local images directory and update Markdown references to relative paths.
  • Selective Processing: Convert an entire PDF or only specified pages and ranges to reduce processing time and API usage.
  • Use Case: Convert a research paper with figures into a self-contained Markdown folder containing the formatted text and extracted images for analysis or note-taking.

Quick Start

Ask the Skill to convert the PDF at 'input.pdf' into a self-contained Markdown folder at 'Output/PDFConversions/paper.md'.

Frequently Asked Questions about mistral-pdf-to-markdown

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

FAQPage Schema
How do I convert a scanned research paper PDF into structured Markdown?▼

You convert a scanned research paper PDF into structured Markdown by using Mistral OCR to extract text and figures, saving the formatted output and images into a self-contained folder with relative paths.

Can I extract embedded images from a PDF during Markdown conversion?▼

Yes, you can extract embedded images from a PDF during Markdown conversion. The Skill saves document images locally and automatically updates Markdown references to point to these relative image paths.

Do I need a Mistral API key to process complex-layout PDFs?▼

Yes, you need a Mistral API key to process complex-layout PDFs. The workflow requires the Mistral OCR API along with the mistralai, pypdf, python-dotenv, and pyyaml packages to resolve configuration and call the OCR service.

Is it possible to convert only specific page ranges of a PDF to Markdown?▼

Yes, it is possible to convert only specific page ranges of a PDF to Markdown. Selective processing allows you to target specified pages, which reduces processing time and minimizes API usage.

What is the best way to transcribe complex-layout PDFs without manual effort?▼

The best way to transcribe complex-layout PDFs without manual effort is using Mistral OCR to convert documents into structured Markdown, preserving document organization and extracting embedded images automatically.

Why does PDF to Markdown conversion fail on scanned documents without OCR?▼

PDF to Markdown conversion fails on scanned documents without OCR because scanned PDFs are image-based and lack selectable text. Applying Mistral OCR resolves this by recognizing text within images to produce structured Markdown.

Related Skills

Explore More Education & Research Skills→
smallnestsmallnest
190

markitdown

Convert PDFs, Word, Excel, HTML, and images with OCR into Markdown.

Community
Advanced
ChrisWilesChrisWiles

wiki-ingest

Ingest Markdown, text, PDFs, web clippings, and images into an Obsidian wiki.

Community
Advanced
ybsaybsa
3

eightctl

Control Eight Sleep pods for status, temperature, alarms, and schedules.

Community
Intermediate
Quill-AgentQuill-Agent
3

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced