skills.rest
djimontyp
djimontypCOMMUNITY
Explore all skills by this author →
Website𝕏@djimontypGitHub

docling

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

Updated Aug 23, 2026
Search Tags:#ocr#data extraction#markdown#document conversion#batch processing#document analysis#pdf parsing
One-click install
npx skills add https://github.com/djimontyp/task-tracker --skill docling-djimontyp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docling
Source: https://github.com/djimontyp/task-tracker/tree/main/.claude/skills/docling
Command: npx skills add https://github.com/djimontyp/task-tracker --skill docling-djimontyp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill eliminates the manual effort of converting documents between formats and extracting structured content from complex files like presentations, PDFs, and spreadsheets.

Core Features & Use Cases

  • Multi-Format Conversion: Convert PPTX, PDF, DOCX, XLSX, images and more to Markdown, JSON, or HTML.
  • AI-Powered Analysis: Use OCR, table extraction, and vision models for accurate content recognition.
  • Use Case: Imagine you have a training course with 20 PowerPoint presentations. Use this Skill to automatically convert them all to clean Markdown files with proper structure and an index.

Quick Start

Use the docling skill to convert the attached presentation file 'quarterly-review.pptx' to Markdown format.

Frequently Asked Questions about docling

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

FAQPage Schema
How do I convert PDF documents to Markdown or JSON format?▼

Convert PDFs to Markdown, JSON, or HTML using docling's AI-powered layout analysis and OCR. The Skill processes single files or batch directories, automatically extracting text, tables, and structure with configurable output formats and optional asset export.

Can I extract tables and structured data from PowerPoint presentations?▼

Extract tables and structured content from PPTX files with AI-powered analysis. Docling recognizes layout, tables, and text, converting them to clean Markdown or JSON with proper hierarchy and formatting for easy indexing and reuse.

What document formats does batch processing support?▼

Batch processing handles PPTX, PDF, DOCX, XLSX, HTML, and images. Convert entire directories at once with slugified output filenames, automatic index generation, and multi-format output (Markdown, JSON, HTML, Text, DocTags) via CLI or Python API.

Does this work with scanned documents and images?▼

Yes, OCR capability recognizes text from scanned PDFs and image files. Configurable OCR modes, table extraction, and optional vision model enrichment enable accurate content extraction from visually complex or handwritten documents.

How do I automate document conversion for large file collections?▼

Use batch directory processing to convert hundreds of files automatically. The Skill generates slugified filenames, creates an index, exports assets, and outputs multiple formats simultaneously via CLI, eliminating manual format conversion workflows.

Can I enrich extracted content with additional metadata or ASR?▼

Optional VLM and ASR enrichment layers add semantic analysis and audio transcription to extracted content. These configurable modes enhance extraction quality and enable downstream indexing, search, and content enrichment workflows.

Related Skills

Explore More Content & Communication Skills→
javierhbrjavierhbr

docling

Parse PDF, DOCX, PPTX, HTML, and images into Markdown, HTML, or JSON.

Community
Advanced
vecearvecear

doc-to-vector-dataset-generator

Convert documents into chunked JSONL datasets with metadata for embedding search.

Community
Advanced
gabergergaberger
4

AgentDB Vector Search

Index documents into embeddings and query vectors with HNSW indexing.

Community
Advanced
zangjeicyzangjeicy

ocr-and-documents

Extract text and structured data from PDFs and scanned documents using OCR.

Community
Intermediate