zerox
by otacu
Image & Video GenerationBrief
Convert documents (PDF, DOCX, PPTX, images, etc.) to Markdown using the zerox library.
Description
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
User asks: convert this scanned PDF to Markdown
- 1
Identify the file path of the target PDF
- 2
Run convert-bg.mjs with the file path for background processing
- 3
Monitor the log file for conversion progress
- 4
Read the output Markdown file once complete
A .md file with the full text content extracted from the scanned PDF
Requirements
- APIYI_API_KEY environment variable (OpenAI-compatible API key)
Installation
clawhub install otacu/zeroxRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.