Automated summary
This skill documents how to use the docling CLI to convert web pages, PDFs, DOCX, PPTX files and images into structured text (Markdown, text, JSON, YAML or HTML), with optional GPU-accelerated OCR.
Strengths
- Covers a broad set of input formats (html, pdf, docx, pptx, image, md, csv, xlsx) and structured output formats
- Draws a clear line between docling for extracting a known URL and web_search for discovering pages
- Ships copy-ready commands plus a concise table of key flags (--from, --to, --device, --ocr)
- Explicitly flags risky options such as remote services, external plugins and untrusted headers
Limitations
- Assumes the docling CLI is already installed and, for GPU use, that NVIDIA CUDA drivers are present
- Gives no guidance on per-format parsing quality or file-size limits
- The full option list lives in an external reference file not included with the skill
Use it when you already have a URL or local file and need clean, structured text extracted from it instead of raw HTML.
Skip it when you need to search or discover pages on the web, or when docling cannot be installed in the environment.
Security analysis
CautionThe skill is documentation for a legitimate document-extraction CLI and does not instruct destructive or exfiltrating actions. It does invoke bash, network access, and OCR/ML processing, and it correctly warns against remote-service/external-plugin flags, so it warrants caution rather than being marked risky.
- •Requires an external `docling` CLI binary plus Python/PyTorch/CUDA environment; actual behavior depends on the installed version and models.
- •Processes arbitrary URLs and documents, which involves network fetching and ML/OCR processing of untrusted content.
- •Extracted web/document content may contain prompt-injection or malicious instructions that downstream agents could misinterpret.
Examples
Use docling to fetch https://example.com/blog/post with --from html --to md into /tmp/docling_out, then read the resulting markdown and summarize its main points.Run docling on /data/contracts/scan.pdf with --ocr --device cuda --output /tmp/docling_out, then extract the parties, dates and payment terms from the output.Convert /data/decks/q3-review.pptx with docling --from pptx --to text --output /tmp/docling_out and give me a bullet outline of each slide.name: docling description: Extract and parse content from web pages, PDFs, documents (docx, pptx), and images using the docling CLI with GPU acceleration. Use INSTEAD of web_fetch for extracting content from specific URLs when you need clean, structured text. Use Brave (web_search) for searching/discovering pages. Use docling when you HAVE a URL and need its content parsed. version: 1.0.2 metadata: requires: bins: ["docling"]
Docling - Document & Web Content Extraction
CLI tool for parsing documents and web pages into clean, structured text. Uses GPU acceleration for OCR and ML models.
Prerequisites
doclingCLI must be installed (e.g., viapipx install docling)- For GPU support: NVIDIA GPU with CUDA drivers
When to Use
- Extract content from a URL → Use docling (not web_fetch)
- Search for information → Use web_search (Brave)
- Parse PDFs, DOCX, PPTX → Use docling
- OCR on images → Use docling
Quick Commands
Web Page → Markdown (default)
docling "<URL>" --from html --to md
Output: creates a .md file in current directory (or use --output)
Web Page → Plain Text
docling "<URL>" --from html --to text --output /tmp/docling_out
PDF with OCR
docling "/path/to/file.pdf" --ocr --device cuda --output /tmp/docling_out
Key Options
| Option | Values | Description |
|--------|--------|-------------|
| --from | html, pdf, docx, pptx, image, md, csv, xlsx | Input format |
| --to | md, text, json, yaml, html | Output format |
| --device | auto, cuda, cpu | Accelerator (default: auto) |
| --output | path | Output directory (recommended: use controlled temp dir) |
| --ocr | flag | Enable OCR for images/scanned PDFs |
| --tables | flag | Extract tables (default: on) |
Security Notes
⚠️ Avoid these flags unless you trust the source:
--enable-remote-services- can send data to remote endpoints--allow-external-plugins- loads third-party code- Custom
--headerswith untrusted values - can redirect requests
Workflow
- For web content extraction: Use
docling "<URL>" --from html --to text --output /tmp/docling_out - Read the output file from the specified output directory
- Clean up the output directory after reading
GPU Support
Docling supports GPU acceleration via CUDA (NVIDIA). Verify CUDA is available:
python -c "import torch; print(torch.cuda.is_available())"
Full CLI Reference
See references/cli-reference.md for complete option list.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/document-extraction-with-docling-mrwakft7' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/document-extraction-with-docling-mrwakft7/download' --output '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md.part' && mv '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md.part' '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Original excerpt: Prerequisites
doclingCLI must be installed (e.g., viapipx install docling)- For GPU support: NVIDIA GPU with CUDA drivers
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md' && test -s '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/docling' && cp -R '.skill-downloads/document-extraction-with-docling-mrwakft7' '.claude/skills/docling'Cursor
test -f '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md' && test -s '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/docling' && cp -R '.skill-downloads/document-extraction-with-docling-mrwakft7' '.cursor/skills/docling'Codex
test -f '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md' && test -s '.skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/docling' && cp -R '.skill-downloads/document-extraction-with-docling-mrwakft7' '.agents/skills/docling'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/document-extraction-with-docling-mrwakft7'openskills read 'document-extraction-with-docling-mrwakft7'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/document-extraction-with-docling-mrwakft7/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.