skills.rest
javierhbr
javierhbrCOMMUNITY
Explore all skills by this author →
GitHub

docling

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

Updated Feb 17, 2026
Search Tags:#ocr#document conversion#rag#text extraction#chunking#document parsing#pdf processing
One-click install
npx skills add https://github.com/javierhbr/random-poc --skill docling-javierhbr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: docling
Source: https://github.com/javierhbr/random-poc/tree/main/custom-skills/beagle-main/plugins/beagle-core/skills/docling
Command: npx skills add https://github.com/javierhbr/random-poc --skill docling-javierhbr

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill tackles the challenge of extracting and understanding information locked within various document formats, making it accessible for further processing and analysis.

Core Features & Use Cases

  • Universal Document Parsing: Handles PDFs, DOCX, PPTX, HTML, images, and many more formats.
  • Text & Structure Extraction: Extracts text, tables, and layout information.
  • Format Conversion: Converts documents to Markdown, HTML, or JSON.
  • RAG Pipeline Ready: Chunks documents for efficient retrieval-augmented generation.
  • Use Case: Automatically convert a batch of research papers (PDFs) into Markdown files, extract key tables from financial reports (DOCX), or prepare image documents for an AI to read and summarize.

Quick Start

Use the docling skill to convert the document located at '/path/to/your/document.pdf' into markdown format.

Frequently Asked Questions about docling

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

FAQPage Schema
How do I extract text and tables from a PDF for a RAG pipeline?▼

To extract text and tables from a PDF for a RAG pipeline, you need a document parsing tool that recognizes layout structures. This Skill handles PDF text extraction, table recognition, and automatically chunks the content for retrieval-augmented generation.

What is the best way to convert PDF and DOCX files to Markdown?▼

The best way to convert PDF and DOCX files to Markdown is by using a universal document parser. This Skill facilitates format conversion from various inputs like DOCX and PDF into Markdown, HTML, or JSON outputs.

Does document parsing support OCR for image-based PDFs?▼

Yes, document parsing supports OCR for image-based documents. This Skill applies optical character recognition to extract text from images and image-based PDFs, making the content accessible for further processing.

Can I extract content from PPTX and HTML files alongside PDFs?▼

Yes, you can extract content from PPTX and HTML files alongside PDFs. This Skill provides universal document parsing that handles a wide array of formats including PPTX, HTML, DOCX, and images.

How do I chunk extracted documents for retrieval-augmented generation?▼

To chunk extracted documents for retrieval-augmented generation, you process the parsed content through a dedicated chunking mechanism. This Skill is RAG pipeline ready and chunks documents efficiently after text extraction and layout recognition.

What are the limitations when processing complex layouts in financial reports?▼

When processing complex layouts in financial reports, limitations depend on the document parsing configuration. This Skill offers advanced configurations for parsing pipelines to optimize table recognition and layout extraction from intricate formats like DOCX.

Related Skills

Explore More Software Engineering Skills→
jackspacejackspace
16

markitdown

Convert PDFs, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, and images into Markdown.

Community
Intermediate
amurataamurata
6

rag-implementation

Implement RAG systems with vector databases and embedding models.

Community
Advanced
Clay-HHKClay-HHK
2

chroma

Store embeddings and metadata for semantic and full-text retrieval.

Community
Intermediate
taracodlabstaracodlabs
779

ocr-and-documents

Extract readable text from PDFs, scanned images, and Word documents using Python libraries.

Official
Intermediate