Setup & Installation
openclaw skills install @otacu/zerox
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install zerox
What This Skill Does
Converts documents, including scanned PDFs, Word files, PowerPoint presentations, and images, to Markdown using GPT-4o vision. Supports both foreground and background processing modes for files of any size.
Uses GPT-4o vision to extract text from scanned documents that traditional OCR tools misread or fail on entirely.
When to use it
- Extract text from a scanned contract PDF
- Convert a PPTX slide deck to Markdown for editing
- Pull content from a DOCX report into a plain text format
- Process a batch of invoice images into structured text
- Convert a legacy PDF manual to searchable Markdown
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: convert this scanned PDF to Markdown
AGENT
- 1Identify the file path of the target PDF
- 2Run convert-bg.mjs with the file path for background processing
- 3Monitor the log file for conversion progress
- 4Read the output Markdown file once complete
OUTPUT
A .md file with the full text content extracted from the scanned PDF
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
APIYI_API_KEY environment variable (OpenAI-compatible API key)