LaunchKit · 2026
Back to Skills

Extract and parse content from web pages, PDFs, documents (docx, pptx), and images using the docling CLI with GPU.

0
868 downloads
by @er3mit4

Setup & Installation

openclaw skills install @er3mit4/docling

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install docling

Version History

v1.0.2Feb 12, 2026 - Version note by skill developer:

Added required bins metadata, security warnings for remote services and plugins, and best practices for output directory

What This Skill Does

Docling is a CLI tool that extracts and parses content from web pages, PDFs, and office documents into clean, structured text. It supports OCR on scanned documents and images using GPU acceleration via CUDA.

Unlike basic HTTP fetchers, docling handles PDFs, scanned images, and complex document formats that return raw binary or malformed HTML.

When to use it

  • Extracting readable text from a research paper PDF
  • Converting a web article to markdown for offline processing
  • Running OCR on a scanned invoice or image
  • Parsing a PPTX slide deck into plain text
  • Pulling structured content from a DOCX report

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: extract the content from this PDF: /tmp/report.pdf

AGENT
  1. 1Run `docling /tmp/report.pdf --ocr --device auto --output /tmp/docling_out`
  2. 2Wait for docling to process the document with OCR
  3. 3Read the output markdown file from /tmp/docling_out
  4. 4Return the parsed text content to the user
  5. 5Clean up /tmp/docling_out
OUTPUT

Clean, structured markdown text extracted from the PDF

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

docling CLI installed (e.g. via pipx install docling)NVIDIA GPU with CUDA drivers (optional, for GPU-accelerated OCR)