An advanced document conversion utility that uses GPT-4o vision to transform complex PDFs and images into clean, structured Markdown.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install zerox
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 zerox 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 Zerox Document Converter?
The Zerox Document Converter is a specialized skill designed to bridge the gap between static file formats and LLM-ready text. By leveraging the zerox library and GPT-4o vision, it accurately extracts text from scanned PDFs, Microsoft Word documents, and images while preserving logical structure. This skill is essential for developers using Openclaw Skills who need to ingest legacy documentation or unstructured data into their AI workflows.
Whether you are dealing with small text-based files or massive scanned volumes, this tool provides the flexibility to process data in the foreground for immediate results or in the background for long-running tasks. It represents a significant upgrade over traditional OCR by using visual reasoning to understand document layouts.
Zerox Document Converter Use Cases
- Extracting text from scanned PDF contracts for automated analysis within Openclaw Skills.
- Converting PowerPoint presentations into Markdown for knowledge base integration.
- Transforming legacy Word documents into clean technical documentation.
- Processing image-based data captures into searchable text formats.
- Automating high-volume document ingestion pipelines.
How Zerox Document Converter Works
- The user specifies a source file path and an optional output destination.
- The skill selects the appropriate execution mode based on the script used (foreground for small files, background for large ones).
- It utilizes GPT-4o vision to analyze the document pages visually, ensuring high accuracy even for handwritten or poorly scanned text.
- The processed content is formatted into Markdown and written to the local file system.
- In background mode, the system monitors progress via logs and sends a system notification upon completion.
Zerox Document Converter Setup
To get started with this skill, ensure you have Node.js installed and your API credentials configured.
# Set your API key
export APIYI_API_KEY='your_openai_compatible_key'
# Install dependencies (if not already handled by the environment)
npm install zerox
# Run a foreground conversion
node scripts/convert.mjs "path/to/doc.pdf"
Zerox Document Converter Data Schema & Taxonomy
The skill organizes its output and tracking data as follows:
| Data Type | Location / Format | Description |
|---|---|---|
| Output Markdown | {baseDir}/output/*.md |
The final converted text file. |
| Background Logs | {baseDir}/output/convert-bg.log |
Real-time progress tracking for async tasks. |
| Environment | APIYI_API_KEY |
Required authentication for the vision model. |
| Supported Input | .pdf, .docx, .pptx, .png, .jpg | Valid source file extensions for Openclaw Skills. |
Zerox Document Converter Advanced Features
- Asynchronous Background Processing: Handles large documents without blocking the terminal or risking timeouts.
- macOS Notification Integration: Real-time alerts when background conversion tasks are finished.
- Vision-Based OCR: Uses advanced AI models to interpret layouts and text that standard OCR tools often miss.
- Detached Execution: Once a background job starts, the terminal can be closed without interrupting the process.
- Customizable Output Mapping: Full control over where converted Markdown files are saved within your Openclaw Skills workspace.
SKILL.md
Loading
Related Openclaw Skills
EdgeHDF5 Memory
A high-performance, HDF5-backed persistent cognitive memory system for AI agents featuring hybrid vector search and temporal decay.
Paperless-ngx Document Management
A powerful integration to programmatically manage documents, tags, and metadata within a Paperless-ngx instance.
Viboost
Viboost is an automated logging utility that tracks every tool call made by your AI agent and syncs it to your public viboost.ai profile.
Browser VPS Setup Skill
A technical skill for deploying a remote-controlled, visually accessible Chrome browser environment on a Linux VPS for agent-driven automation.
Content ID Guide
A procedural clarity tool designed to help creators organize documentation and understand the workflow of automated copyright claims.
Skill Namer (Portmanteau Forge)
A specialized naming engine for creating short, high-traction portmanteaus and primitives optimized for the AI agent economy and ENS domains.
Featured*
