A comprehensive self-hosted PDF manipulation suite providing over 60 tools for document processing via a robust REST API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install stirling-pdf
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 stirling-pdf 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 Stirling-PDF?
This skill brings the power of Stirling-PDF to your agentic environment, offering a wide array of document manipulation capabilities. By leveraging a self-hosted instance, Openclaw Skills can perform complex tasks such as OCR, redaction, and format conversion without sending sensitive data to external third-party services. It provides a bridge between your local files and a professional-grade PDF processing engine.
Whether you need to organize page structures, compress large files for storage, or secure documents with passwords, this integration ensures high-performance processing. It is designed for developers who require a private, scalable, and API-driven approach to PDF management within their Openclaw Skills ecosystem.
Stirling-PDF Use Cases
- Automating the conversion of scanned image documents into searchable PDFs using OCR.
- Batch merging multiple report components into a single, cohesive document.
- Standardizing corporate documents by adding watermarks and stamps programmatically.
- Reducing file sizes for web distribution through advanced compression algorithms.
- Securing sensitive financial records by applying passwords and removing metadata.
How Stirling-PDF Works
- The user or agent triggers a specific PDF operation using the provided wrapper script or a direct API call.
- The skill identifies the correct Stirling-PDF endpoint based on the requested operation (e.g., merge, split, or compress).
- Local files are prepared and sent as multipart/form-data to the self-hosted Stirling-PDF server instance.
- The server processes the request using its internal logic and returns the modified file as a binary stream.
- The skill saves the output to the designated path, completing the automated workflow within the Openclaw Skills framework.
Stirling-PDF Setup
To use this skill, you must have a running instance of Stirling-PDF and the necessary CLI tools. Configure your environment by setting the following variables:
export STIRLING_PDF_URL="http://localhost:8080"
export STIRLING_API_KEY="your_optional_api_key"
Ensure that node and curl are installed on your system. You can then run operations using the provided script:
node ~/.openclaw/skills/stirling-pdf/scripts/pdf.js ocr input.pdf -o output.pdf
Stirling-PDF Data Schema & Taxonomy
The skill manages data primarily through file paths and API parameters. The following table describes how data is handled during a typical request:
| Parameter | Description |
|---|---|
| fileInput | The multipart file data sent to the Stirling-PDF API. |
| operation | The specific task identifier (e.g., 'merge', 'ocr', 'sign'). |
| STIRLING_PDF_URL | The base endpoint for all Openclaw Skills API requests. |
| output | The destination path for the processed PDF document. |
Stirling-PDF Advanced Features
- Access to over 60 specialized PDF tools through a single integrated skill.
- Support for complex OCR (Optical Character Recognition) in multiple languages.
- Bidirectional conversion between PDF and Office formats like Word, Excel, and Powerpoint.
- Granular security controls including redaction of sensitive content and metadata sanitization.
- Direct integration with Swagger UI for exploring and testing custom API endpoints.
SKILL.md
Loading
Related Openclaw Skills
Ragflow API Client
A universal API client for managing knowledge bases and performing Retrieval-Augmented Generation (RAG) within self-hosted Ragflow instances.
PMC Harvest
A specialized utility for searching and harvesting full-text scientific articles and metadata from PubMed Central using official NCBI APIs.
Mealie
A powerful API client for Mealie that lets you manage recipes, meal plans, and shopping lists through AI-driven workflows.
Crawl4AI Web Scraper
A powerful web scraping skill for AI agents that leverages local Crawl4AI instances to extract full-page content with JavaScript rendering.
Research Swarm TNBC Research Skill
A collaborative multi-agent skill for conducting and reviewing scientific research on Triple-Negative Breast Cancer.
Financial Analyst
A professional-grade financial analysis tool for generating DCF models, comparable company analysis, and equity research reports with transparent assumptions.
Featured*
