A high-performance PDF to Markdown converter that extracts text, tables, and complex formulas using the MinerU Open API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pdftomd
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pdftomd using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is pdf2md?
pdf2md is a specialized utility designed for AI agents and developers to transform unstructured PDF documents into clean, machine-readable Markdown. By leveraging the MinerU Open API, it handles the heavy lifting of parsing complex layouts, including academic formulas and multi-column tables, without requiring manual data entry or complex OCR setups. As part of the Openclaw Skills ecosystem, it provides a seamless bridge between static documents and LLM-ready text.
The tool is built for speed and accessibility, offering a stateless processing model that requires no authentication for standard tasks. Whether you are dealing with local files or remote URLs, this skill ensures that PDF content is instantly available for summarization, analysis, or integration into automated documentation workflows.
pdf2md Use Cases
- Converting academic papers or technical reports into Markdown for LLM analysis.
- Extracting structured table data from financial PDF statements.
- Parsing mathematical formulas from research documents into LaTeX-compatible Markdown.
- Automating the ingestion of PDF-based documentation into a static site generator or knowledge base.
- Quick summarization of remote PDF whitepapers via direct URL input.
How pdf2md Works
- The user provides a local path or a remote URL of a PDF document to the CLI.
- The pdf2md skill utilizes the mineru-open-api to transmit the document to the MinerU processing engine.
- The engine performs layout analysis to identify text blocks, tables, and formulas.
- The document is converted into a structured Markdown format, applying language hints if provided.
- The clean Markdown output is returned to the terminal or saved to a specified local directory for immediate use.
pdf2md Setup
You can install the necessary components for this Openclaw Skills integration using your preferred package manager:
Using npm:
npm install -g mineru-open-api
Using uv (Python):
uv tool install mineru-open-api
Using Go (Darwin/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
pdf2md Data Schema & Taxonomy
The skill follows a straightforward data flow focused on transforming binary PDF data into text-based Markdown structures:
| Component | Description |
|---|---|
| Input Sources | Local .pdf files or public https:// URLs. |
| Output Format | Standard Markdown (.md) text. |
| Metadata | Supports --pages for range selection and --language (ch/en) for OCR optimization. |
| Storage | Stateless processing; files are processed in-memory or saved to an optional -o output directory. |
| Constraints | Free tier supports up to 10MB or 20 pages per document. |
pdf2md Advanced Features
- Direct URL Processing: Extract content from web-hosted PDFs without downloading them first.
- Formula Recognition: Specialized handling for mathematical symbols and equations.
- Page Range Targeting: Extract specific chapters or sections using the --pages flag.
- Language Hinting: Improve extraction accuracy by specifying English or Chinese language contexts.
- High-Capacity Upgrade: Seamless transition to the
extractcommand for files up to 200MB (requires auth).
SKILL.md
Loading
Related Openclaw Skills
SimpleTexting
A robust integration for SimpleTexting that enables AI agents to manage SMS marketing campaigns, contact lists, and automated messaging.
Agent Essentials
A meta-skill for AI agents designed to expand functional capabilities through skill discovery and ensure continuous self-improvement by capturing durable lessons.
Novel Writer
A creative writing specialist designed to craft high-pacing urban science fiction novels with a blend of daily life and futuristic elements.
Custom Grok Search
A powerful search utility enabling AI agents to access real-time web data and X/Twitter discussions via xAI Grok APIs.
Amazon Competitor Analysis
A comprehensive competitive intelligence tool that breaks down listing quality, pricing strategies, and review sentiment to give you a market edge.
Short Video Auto-Processor
An automated toolkit for video speech recognition, subtitle generation, and AI-driven title extraction to streamline social media content creation.
METADATA
Featured*
