use-docling

Convert and extract content from local documents using the docling CLI.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/skaile-ai/ai-assets --skill use-docling
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: use-docling
Source: https://github.com/skaile-ai/ai-assets/tree/main/use/skills/use-docling
Command: npx skills add https://github.com/skaile-ai/ai-assets --skill use-docling

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

In many workflows, teams need offline, privacy-conscious document processing that does not rely on external APIs to convert formats, extract content, or transcribe audio. Docling provides a local CLI to handle these tasks end-to-end.

Core Features & Use Cases

  • Local document conversion: convert PDFs, Word documents, HTML, and more to Markdown, JSON, HTML, or plain text using the docling CLI.
  • OCR and automated text extraction: enable OCR for images and scanned PDFs to recover readable text.
  • Image handling and artifacts: export embedded images as referenced artifacts or embed them directly in outputs.
  • Audio transcription: transcribe audio files into text using built-in or pluggable ASR models.
  • Use cases include archiving research papers, digitizing contracts, and extracting tables or metadata for data pipelines.

Quick Start

Run docling on a sample file to convert it to Markdown with default settings.

Frequently Asked Questions about use-docling

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

FAQPage Schema
How do I convert PDFs to Markdown locally without using external APIs?

To convert PDFs to Markdown locally, you can use a local CLI to process documents offline, ensuring privacy-conscious extraction without relying on external APIs. This approach supports converting PDFs and Word documents directly into Markdown formats.

Does the docling CLI support OCR for extracting text from scanned PDFs and images?

Yes, OCR is supported for scanned PDFs and images to recover readable text. By enabling OCR during local document processing, you can extract content from image-based files and export it to formats like Markdown or plain text.

What is the best way to transcribe audio files into text offline?

The best way to transcribe audio offline is using a local CLI with built-in or pluggable ASR models. This allows you to perform automated speech recognition locally, converting audio files into readable text without external API dependencies.

Can I extract embedded images from documents and export them as artifacts?

Yes, you can handle embedded images and export them as referenced artifacts or embed them directly in outputs. This image handling capability works across various document formats during local conversion to Markdown or JSON.

What output formats are available when converting Word documents and HTML locally?

Available output formats include Markdown, JSON, HTML, and plain text. When converting Word documents and HTML files locally, the CLI processes the content and exports it into your chosen format for archiving or digitization.