A high-performance CLI tool and AI agent skill that transforms Word, PowerPoint, and Excel files into clean Markdown format using the MinerU Open API.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install document-to-markdown
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install document-to-markdown using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Document to Markdown skill is a powerful utility designed for developers and AI agents who need to bridge the gap between legacy office formats and modern Markdown workflows. By leveraging the MinerU Open API, this tool provides a seamless way to extract structured text from complex document types without the friction of manual copy-pasting or complex parsing libraries. This is an essential addition to any Openclaw Skills collection for users working with RAG (Retrieval-Augmented Generation) or automated content pipelines.
What sets this skill apart is its zero-config philosophy. It requires no API keys, no signups, and no authentication for standard document extraction. Whether you are dealing with local files or remote URLs, the skill ensures that document structures, headers, and tables are preserved, making the content immediately ready for AI analysis or static site generation.
You can install the necessary components for this Openclaw Skills integration using your preferred package manager:
# Install via npm
npm install -g mineru-open-api
# Or install via uv
uv tool install mineru-open-api
# Or install via Go (Darwin/Linux)
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
After installation, verify the setup by running:
mineru-open-api flash-extract --help
The skill follows a straightforward input-output schema designed for high interoperability with other Openclaw Skills.
| Attribute | Specification |
|---|---|
| Supported Formats | .docx, .pptx, .xls, .xlsx |
| Input Methods | Local file path or Public URL |
| Output Format | Standard Markdown (.md) |
| File Size Limit | Max 10MB per document (Flash mode) |
| Page Limit | Max 20 pages per document (Flash mode) |
| Data Privacy | Real-time processing; no persistent storage after extraction |
-o flag for high-volume conversion tasks.extract command for documents up to 200MB or 600 pages (requires account authentication).Loading
A professional framework for designing deep testing strategies that move beyond code coverage to focus on risk alignment, test pyramids, and CI reliability.

A comprehensive framework for modeling domain and UI state, ensuring data consistency across client-side and hybrid applications.

A specialized configuration utility to bridge Weibo channel credentials with the OpenClaw ecosystem.

A comprehensive six-stage database performance workflow for diagnosing symptoms, analyzing execution plans, and implementing verified query and index optimizations.

A professional-grade AI video editor that automates complex editing tasks like silence removal and captioning through natural language commands.

A specialized skill designed to guide users through the process of connecting OpenClaw agents to Discord for multi-bot collaboration.








































