An intelligent PDF processing tool that extracts text, formulas, and tables from complex documents using the MinerU API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install smart-pdf-reader
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 smart-pdf-reader 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 Smart PDF Reader?
The Smart PDF Reader is a sophisticated document analysis tool designed to bridge the gap between static PDF files and actionable AI context. As part of the Openclaw Skills library, it utilizes the mineru-open-api to handle everything from simple text documents to complex, multi-column academic papers and scanned archives. This skill empowers AI agents to read, summarize, and extract data with high precision, supporting both fast token-free extraction and deep OCR-based processing.
By integrating this skill, developers can automate the ingestion of technical reports, financial statements, and research papers. The skill is optimized for the Openclaw Skills framework, ensuring that extracted Markdown is perfectly formatted for LLM consumption, whether the source is a digital PDF or a low-quality scan requiring advanced formula detection.
Smart PDF Reader Use Cases
- Summarizing multi-column academic journals and research papers with high layout fidelity.
- Digitizing scanned archives and legal documents using integrated OCR capabilities.
- Extracting structured data and formulas from technical manuals or financial reports.
- Performing instant, token-free content previews of small PDF files via flash extraction.
- Automating document review workflows within the Openclaw Skills environment.
How Smart PDF Reader Works
- The AI agent detects a PDF document and selects the appropriate extraction strategy based on file size and complexity.
- For simple files, the flash-extract command is executed to stream Markdown directly to the agent's context.
- For complex or scanned documents, the skill triggers a precision extract using OCR and table recognition flags.
- The mineru-open-api processes the file and generates structured Markdown output in a designated directory.
- The agent reads the resulting Markdown to provide summaries, answer questions, or perform further data analysis.
Smart PDF Reader Setup
To get started with this component of Openclaw Skills, install the MinerU CLI tool globally:
npm install -g mineru-open-api
Ensure your agent has the necessary permissions to execute bash commands and access the file system for document processing.
Smart PDF Reader Data Schema & Taxonomy
The Smart PDF Reader organizes its output into structured directories to ensure data persistence and easy retrieval within the Openclaw Skills workflow.
| Feature | Specification |
|---|---|
| Output Directory | ~/MinerU-Skill/<name>_<hash>/ |
| Output Format | Structured Markdown (.md) |
| Extraction Modes | Flash (stdout), Precision (file-based), VLM (Layout-aware) |
| Asset Handling | Extracted images and tables are stored alongside the Markdown file |
Smart PDF Reader Advanced Features
- Vision Language Model (VLM) support for superior layout analysis in academic papers.
- Flash-extract mode for zero-token cost reading of standard digital PDFs.
- Comprehensive table and mathematical formula recognition for technical documentation.
- Intelligent directory management using hash-based naming to prevent file collisions in Openclaw Skills automation.
- Support for multilingual OCR to process international documents and archives.
SKILL.md
Loading
Related Openclaw Skills
Excel Export
A specialized utility for AI agents to generate professional, multi-sheet Excel workbooks from structured JSON data using Openclaw Skills.
AI PDF Converter
A high-performance AI document processing tool that converts PDFs into structured formats like Markdown, HTML, and DOCX using intelligent layout analysis.
Context Usage Checker
A smart utility to monitor, visualize, and manage your AI session's token consumption and remaining context window.
Smart PDF OCR
An intelligent document processing skill powered by the MinerU API for high-precision OCR and layout analysis of scanned PDFs.
PDF to Text Extraction (MinerU)
Extract high-quality text from PDFs using the MinerU API with support for OCR and batch processing.
Feishu Image Send
A specialized tool that ensures images are rendered inline in Feishu chats by bypassing standard path restrictions through direct API integration.
Featured*
