skills.rest
SillyHippy
SillyHippyCOMMUNITY
Explore all skills by this author →
GitHub

docling-ocr

Convert PDFs, Word documents, and images to Markdown using IBM Docling.

Updated Sep 5, 2026
Search Tags:#ocr#pdf#markdown#document conversion#python#docx#docling
One-click install
npx skills add https://github.com/SillyHippy/zo-skills --skill docling-ocr-sillyhippy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docling-ocr
Source: https://github.com/SillyHippy/zo-skills/tree/main/skills/docling-ocr
Command: npx skills add https://github.com/SillyHippy/zo-skills --skill docling-ocr-sillyhippy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docling, and includes scripts (resource) components.

What problem does it solve? Converting documents like PDFs, DOCX files, and images into clean, structured Markdown usually requires manual copy-pasting or complex tooling. This Skill automates that conversion locally, producing Markdown output ready for documentation, note-taking, or downstream text processing. ## Core Features & Use Cases - Multi-Format Conversion: Converts PDF, DOCX, and image files into structured Markdown using IBM's Docling library. - CPU-Only Operation: Runs entirely on CPU with no GPU requirement, suitable for standard Linux environments. - Automatic Dependency Setup: Checks for and installs the docling Python package automatically on first run. - Use Case: You receive a vendor report as a PDF and need its content in Markdown for your knowledge base. Run the conversion script and get a clean .md file saved alongside the original. ## Quick Start Ask the AI to convert your PDF or Word document to Markdown using the docling-ocr skill, providing the path to your input file.

Frequently Asked Questions about docling-ocr

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

FAQPage Schema
How do I convert a PDF to Markdown in Python?▼

Use the convert.py script with the input file path as an argument. It uses IBM's Docling DocumentConverter to parse the PDF and exports the result as Markdown, saving it as a .md file next to the original or at a path you specify.

What file formats does Docling support for conversion?▼

Docling converts PDFs, Word documents (DOCX), and images into Markdown. The script accepts any input file path and produces a structured Markdown output file.

Does Docling require a GPU to run?▼

No, Docling runs entirely on CPU and does not require a GPU. This makes it suitable for standard Linux environments and virtual machines without graphics hardware.

How do I install the docling Python package?▼

The convert.py script handles installation automatically. If docling is not found, it runs pip install docling before converting, though the first install may take a few minutes to download models.

Why is the first Docling conversion slow?▼

The initial run takes longer because pip downloads and installs the docling package along with its required models. Subsequent conversions skip this step and run faster.

Related Skills

Explore More Content & Communication Skills→
wuyyyyyouwuyyyyyou

recipe-save-email-attachments

Save Gmail attachments to a designated Google Drive folder.

Community
Intermediate
managedcodemanagedcode
466

dotnet-managedcode-markitdown

Convert office and rich-text documents to Markdown for .NET applications.

Official
Intermediate
innV0innV0

Source Processor

Extract structured information from PDFs, images, and plain text into metadata-enriched Markdown.

Official
Advanced
spoonbobospoonbobo

doc-convert

Convert PDFs, DOCX, and images to text, markdown, or searchable PDFs.

Community
Intermediate