A high-performance PDF-to-Markdown extraction tool supporting OCR, formulas, and complex table layouts via the MinerU API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mineru-pdf-extractor
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 mineru-pdf-extractor 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 MinerU PDF Extractor?
The MinerU PDF Extractor is a versatile community-driven skill designed to bridge the gap between static PDF documents and LLM-ready structured data. By leveraging the MinerU API, this tool excels at recognizing complex elements like mathematical formulas, nested tables, and scanned text via high-quality OCR. Whether you are building a RAG pipeline or a research assistant, this addition to your Openclaw Skills library provides a robust way to ingest document intelligence.
The skill offers two distinct workflows: a multi-step local file upload for private documents and a streamlined two-step process for online URLs. It is built for developers who need precision and speed when converting academic papers, technical manuals, or business reports into clean Markdown format.
MinerU PDF Extractor Use Cases
- Converting academic papers with complex LaTeX formulas into Markdown for LLM training.
- Extracting data from multi-page business reports with intricate tables for automated analysis.
- Processing scanned PDF documents using OCR to create searchable knowledge bases.
- Streamlining the ingestion of online research papers directly from arXiv via URL.
- Batch processing large directories of local PDF files for data migration projects.
How MinerU PDF Extractor Works
- The user provides a local PDF file path or a public document URL to the skill scripts.
- For local files, the skill applies for a secure upload URL from the MinerU API, uploads the file, and initializes a parsing batch.
- For online URLs, the skill submits a task ID directly to the MinerU engine for faster processing.
- The skill polls the MinerU API status endpoint at defined intervals to track the extraction progress.
- Once complete, the skill downloads a comprehensive ZIP package containing the converted Markdown and supporting assets.
- Finally, the skill automatically extracts the package, organizing the Markdown text, images, and layout metadata for immediate use.
MinerU PDF Extractor Setup
Ensure you have an API key from MinerU and that curl and unzip are installed on your system. These tools are fundamental to the operation of Openclaw Skills in this category.
# Set your authentication token
export MINERU_TOKEN="your_api_token_here"
# Optional: Install jq for better JSON handling
# sudo apt-get install jq
Navigate to the scripts directory to begin using the provided automation utilities.
MinerU PDF Extractor Data Schema & Taxonomy
The skill organizes output into a structured directory for every processed document, ensuring compatibility with other Openclaw Skills that require structured input:
| File | Description |
|---|---|
| full.md | The primary Markdown output containing text, formulas, and table data. |
| images/ | A subdirectory containing all graphical elements extracted from the PDF. |
| content_list.json | A structured JSON representation of the document hierarchy. |
| layout.json | Detailed metadata regarding the document layout and coordinates. |
MinerU PDF Extractor Advanced Features
- Multi-model layout selection: Choose between doclayout_yolo for speed or layoutlmv3 for high-precision accuracy.
- Language detection: Supports specific language hints (Chinese, English) or auto detection for global document support.
- Batch Automation: Includes bash script templates for processing entire directories or lists of URLs sequentially.
- Security-first design: Implements input sanitization and secure environment variable handling for API tokens within the Openclaw Skills ecosystem.
- Extensible shell scripts: Easily integrate the polling and download logic into larger CI/CD or data ingestion pipelines.
SKILL.md
Loading
Related Openclaw Skills
Excalidraw Diagram Generator
Transform text descriptions into beautiful, hand-drawn diagrams and architecture charts rendered as high-quality PNG images.
TS API Miner
An intelligent assistant for analyzing TypeScript files to extract API interfaces, request structures, and JSDoc comments into structured Markdown documentation.
Plan-I (Workflow Initialization)
A dedicated initialization tool that transforms user ideas into structured planning documents to kickstart AI-driven development workflows.
plan-c
An AI agent skill designed to continue and refine project plans through intelligent context recognition and deep codebase exploration.
Eywa
A sophisticated multi-agent coordination layer providing shared spatial memory and swarm navigation for distributed AI agents.
OpenClaw Agent Builder
A comprehensive framework for architecting and managing specialized AI agents with independent sessions, personalities, and sandboxed environments.
METADATA
Featured*
