A Python-powered utility for extracting plain text and comprehensive metadata from PDF documents using PyMuPDF.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install iyeque-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 iyeque-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 PDF Reader Skill?
The PDF Reader skill is a robust tool within the Openclaw Skills library designed to streamline the processing of document data for AI agents. By leveraging the speed and reliability of the PyMuPDF library, this skill enables agents to look inside PDF files, retrieve their content, and understand their internal structure.
This skill is particularly valuable for developers building automated research assistants or document analysis pipelines. It transforms static PDF files into searchable, machine-readable text and structured JSON metadata, making it a cornerstone for any workflow involving Openclaw Skills and document management.
PDF Reader Skill Use Cases
- Summarizing long documents by extracting text for LLM processing.
- Automating the organization of file libraries based on document author or creation date.
- Performing targeted searches within specific page ranges of large reports.
- Verifying the encryption status and format version of uploaded documents.
How PDF Reader Skill Works
- The agent invokes the skill with a file path and a specific command (extract or metadata).
- For text extraction, the PyMuPDF engine parses the document and pulls plain text content, respecting any page limits provided.
- For metadata retrieval, the skill inspects the PDF header and internal dictionary to gather information such as title, author, and producer.
- The resulting data is returned as either a text stream or a structured JSON object for further processing within the Openclaw Skills ecosystem.
PDF Reader Skill Setup
To integrate this skill into your environment, ensure you have Python 3 and the PyMuPDF package installed. Use the following commands to get started:
# Install the necessary dependency
pip install PyMuPDF
# Run a text extraction command
python3 skills/pdf-reader/reader.py extract /path/to/document.pdf --max_pages 5
# Retrieve document metadata
python3 skills/pdf-reader/reader.py metadata /path/to/document.pdf
PDF Reader Skill Data Schema & Taxonomy
The skill returns data in two primary formats depending on the command used. The metadata command produces a JSON object with the following schema:
| Property | Description |
|---|---|
| title | The title of the document as defined in its properties. |
| author | The individual or entity that created the file. |
| subject | The topic or category of the document content. |
| creationDate | The original timestamp when the PDF was generated. |
| format | The version of the PDF standard used (e.g., 1.7). |
| encryption | Details regarding password protection or encryption status. |
PDF Reader Skill Advanced Features
- Large document handling via the max_pages parameter to prevent memory overflow.
- Robust error handling for encrypted or malformed PDF files.
- High-speed performance optimized for integration with other Openclaw Skills.
- Support for detailed PDF versioning and producer identification.
SKILL.md
Loading
Related Openclaw Skills
Local System Info
A lightweight monitoring tool for retrieving real-time system metrics including CPU, memory, disk usage, and active processes.
Audio Processing Skill
A comprehensive audio manipulation toolkit for transcribing, generating, and transforming audio files with AI-powered precision.
Audio Processing
A comprehensive toolset for audio ingestion, analysis, transformation, and generation using Whisper and Librosa.
Mei Hua Yi Shu (Plum Blossom Divination)
A sophisticated computational implementation of the traditional Mei Hua Yi Shu divination system based on hour and minute parameters.
Local System Info
Monitor local system resources including CPU, memory, disk usage, and running processes directly through your AI agent.
Pipe17 Unified Commerce API
A powerful skill for searching and managing orders, shipping requests, fulfillments, and inventory via the Pipe17 Unified API.
METADATA
Featured*
