zerox
Convert documents (PDF, DOCX, PPTX, images, etc.) to Markdown using the zerox library. Use when the user needs to extract text content from document files.
Why use this skill?
Convert PDFs, Word docs, PPTX, and images to Markdown automatically with the zerox AI skill. Supports OCR, background processing, and GPT-4o vision.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/otacu/zeroxWhat This Skill Does
The zerox skill is a powerful document conversion agent designed to transform a wide variety of static file formats into clean, structured Markdown. By leveraging the advanced capabilities of GPT-4o vision, it acts as an intelligent OCR and layout-parsing engine. Whether you are dealing with a standard text-based PDF, a complex Microsoft Word document, a PowerPoint presentation, or a simple image, zerox extracts the textual information and maintains formatting, making it ideal for tasks requiring data extraction, knowledge base population, or document transformation.
Installation
To integrate this skill into your environment, use the OpenClaw skill installer. Open your terminal and execute the following command:
clawhub install openclaw/skills/skills/otacu/zerox
Ensure that you have an OpenAI-compatible API key set in your environment variables under the key APIYI_API_KEY, as the conversion process relies on external model inference to perform accurate recognition.
Use Cases
This skill is highly versatile for professionals and developers alike. Use it to digitize physical archives by converting scanned PDF invoices or records into searchable Markdown. It is also excellent for technical documentation workflows, such as converting legacy DOCX specs or PPTX project summaries into Markdown files that can be easily version-controlled in Git repositories. For researchers, it provides a seamless way to convert images of textbooks or journals into structured text for further AI analysis.
Example Prompts
- "Convert the scanned project report located at /data/documents/report_final.pdf to markdown so I can edit it in Obsidian."
- "Use the background converter for the large training manual at /uploads/guide.pdf and notify me when it is finished."
- "Extract the content from my presentation deck at /files/marketing-q4.pptx and save it to the output folder."
Tips & Limitations
For optimal performance, always choose the correct script based on your file size. The standard convert.mjs script is perfectly fine for quick, short documents. However, for high-page-count PDFs or heavy images, you must use the convert-bg.mjs script; this prevents process timeouts and provides a reliable way to monitor progress via the log files. Note that because this uses GPT-4o, large documents will consume more tokens, potentially impacting your API costs. Always verify the generated Markdown, as complex tables or highly non-standard layouts might occasionally require minor manual cleanup.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-otacu-zerox": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api