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.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install docling或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install docling⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/docling/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- 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"] ---
CLI tool for parsing documents and web pages into clean, structured text. Uses GPU acceleration for OCR and ML models.
docling CLI must be installed (e.g., via pipx install docling)docling "<URL>" --from html --to mdOutput: creates a .md file in current directory (or use --output)
docling "<URL>" --from html --to text --output /tmp/docling_outdocling "/path/to/file.pdf" --ocr --device cuda --output /tmp/docling_out| 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) |
⚠️ Avoid these flags unless you trust the source:
--enable-remote-services - can send data to remote endpoints--allow-external-plugins - loads third-party code--headers with untrusted values - can redirect requestsdocling "" --from html --to text --output /tmp/docling_out Docling supports GPU acceleration via CUDA (NVIDIA). Verify CUDA is available:
python -c "import torch; print(torch.cuda.is_available())"See references/cli-reference.md for complete option list.
安装 Docling 后，可以对 AI 说这些话来触发它
Help me get started with Docling
Explains what Docling does, walks through the setup, and runs a quick demo based on your current project
Use Docling to extract and parse content from web pages, PDFs, documents (docx, pp...
Invokes Docling with the right parameters and returns the result directly in the conversation
What can I do with Docling in my documents & notes workflow?
Lists the top use cases for Docling, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/docling/ 目录（个人级，所有项目可用），或 .claude/skills/docling/（项目级）。重启 AI 客户端后，用 /docling 主动调用，或让 AI 根据上下文自动发现并使用。
Docling 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Docling 可免费安装使用。请查阅仓库了解许可证信息。
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.
Docling 属于「Documents & Notes」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my documents & notes tasks using Docling
Identifies repetitive steps in your workflow and sets up Docling to handle them automatically