skills.rest
ericgandrade
ericgandradeCOMMUNITY
Explore all skills by this author →
GitHub

docling-converter

Convert PDF, DOCX, PPTX, XLSX, HTML, and images into Markdown and JSON.

65|11|Updated Feb 1, 2026
Search Tags:#ocr#markdown#json#batch-processing#docling#document-conversion
One-click install
npx skills add https://github.com/ericgandrade/claude-superskills --skill docling-converter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docling-converter
Source: https://github.com/ericgandrade/claude-superskills/tree/main/skills/docling-converter
Command: npx skills add https://github.com/ericgandrade/claude-superskills --skill docling-converter

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Convert raw, unstructured documents into reliable, structured Markdown and JSON for easy ingestion into knowledge bases and AI pipelines.

Core Features & Use Cases

  • Multi-Format Support: PDF, DOCX, PPTX, XLSX, HTML, Images.
  • OCR integration for scanned documents.
  • Batch processing and scalable conversions for directories.
  • Use Case: Ingest a collection of reports into a searchable knowledge base and extract structured data.

Quick Start

Invoke the converter on a document to produce Markdown and JSON outputs.

Frequently Asked Questions about docling-converter

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

FAQPage Schema
How do I convert PDF documents to structured Markdown for an AI knowledge base?▼

This tool converts PDF documents into structured Markdown and JSON representations, making them ready for ingestion into AI knowledge bases and downstream data pipelines with optional OCR support.

Can I batch process multiple DOCX and PPTX files into JSON at once?▼

Yes, you can batch process multiple DOCX and PPTX files into JSON at once. The converter supports scalable batch conversions for entire directories to streamline archival processes.

Does the document conversion tool support OCR for scanned PDFs and images?▼

The document conversion tool does support OCR for scanned PDFs and images. It integrates OCR capabilities within the Docling runtime to extract text from image-based documents during conversion.

What file formats are supported when extracting structured data from documents?▼

Supported file formats when extracting structured data from documents include PDF, DOCX, PPTX, XLSX, HTML, and images, all of which can be transformed into structured Markdown and JSON representations.

Do I need to install Docling to convert HTML files to Markdown?▼

Yes, you need to install the Docling runtime to convert HTML files to Markdown. The converter requires this dependency to run its core document transformation and optional table extraction features.

What is the best way to extract tables from PDF files for downstream workflows?▼

The best way to extract tables from PDF files is using this converter with the Docling runtime, which provides optional table extraction capabilities to generate structured JSON representations for downstream AI workflows.

Related Skills

Explore More Content & Communication Skills→
tassiovaletassiovale
13

liteparse

Extract text and bounding boxes from PDFs, Office files, and images.

Community
Intermediate
karrtik159karrtik159

rag-implementation

Build RAG systems with vector databases and semantic search.

Community
Advanced
vm0-aivm0-ai
76

pdf4me

Convert, merge, split, OCR, and protect PDF documents via REST API.

Official
Advanced
Monjyu1101Monjyu1101
1

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf and marker-pdf.

Community
Intermediate