skills.rest
takusaotome
takusaotomeCOMMUNITY
Explore all skills by this author →
GitHub

docling-converter

Convert PDFs, office documents, and images into Markdown and structured formats.

5|4|Updated Nov 9, 2025
Search Tags:#ocr#pdf#markdown#document conversion#json#batch processing#docling
One-click install
npx skills add https://github.com/takusaotome/claude-skills-library --skill docling-converter-takusaotome
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docling-converter
Source: https://github.com/takusaotome/claude-skills-library/tree/main/skills/docling-converter
Command: npx skills add https://github.com/takusaotome/claude-skills-library --skill docling-converter-takusaotome

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill removes the friction of manually reformatting and extracting content from PDFs and office files by converting them into clean, reusable text or structured data.

Core Features & Use Cases

  • Universal document conversion: Convert PDF, DOCX, PPTX, HTML, images, Excel (and more) into Markdown, JSON, YAML, HTML, or plain text.
  • OCR for scanned documents: Extract text from image-based pages using OCR, including Japanese via language selection.
  • Workflow-ready outputs: Produce single or multiple formats into a chosen output directory, enabling downstream processing and search.

Quick Start

Run docling-converter on your file to convert it to Markdown and write the output files to the default locations.

Frequently Asked Questions about docling-converter

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

FAQPage Schema
How do I convert a PDF to Markdown or JSON for downstream editing?▼

To convert a PDF to Markdown or JSON, use docling-converter to extract text, tables, and metadata into clean formats. It routes outputs to a chosen directory, enabling downstream processing, search indexing, or analysis.

Can I extract text from scanned PDF pages or images using OCR?▼

Yes, you can extract text from scanned PDF pages or images using OCR. By invoking the docling CLI with an optional OCR language parameter, it processes image-based pages, including Japanese, into editable text.

What is the best way to batch convert office documents into structured data?▼

The best way to batch convert office documents into structured data is using docling-converter. It supports batch processing of files like DOCX, PPTX, and Excel into Markdown, JSON, YAML, HTML, or plain text.

Does docling-converter support extracting tables from PDF and Excel files?▼

Yes, docling-converter supports extracting tables from PDF and Excel files. It parses documents to capture text, tables, and metadata, converting them into structured formats like JSON or Markdown for reuse.

How do I route converted document outputs to a specific directory?▼

You route converted document outputs to a specific directory by invoking the docling CLI with an optional output directory parameter. This allows you to produce single or multiple formats into a chosen location for workflow readiness.

Related Skills

Explore More Data & Analytics Skills→
Wike-CHIWike-CHI
2

document-pro

Extract text, tables, and images from PDFs, DOCX, PPTX, XLSX, and plain text.

Community
Intermediate
LuisElPotiLuisElPoti

tavily-extract

Extract clean markdown or text content from web URLs via Tavily CLI.

Community
Intermediate
TurnaboutHeroTurnaboutHero
12

data-wizard

Automate ETL and data transformation for CSV, JSON, and database sources using Python and pandas.

Community
Advanced
eugenelimeugenelim
15

file-to-markdown

Convert documents and images into Markdown using Docling and deterministic tiling.

Community
Advanced