# Yao Ocr

OCR text recognition expert.

- Repository: https://github.com/YaoApp/yao (8244 stars)
- Category: Business
- License: see repository
- Last updated: 2026-10-19
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add YaoApp/yao --skill yao-ocr -g -a claude-code -y`
Codex: `npx skills add YaoApp/yao --skill yao-ocr -g -a codex -y`
Cursor: `npx skills add YaoApp/yao --skill yao-ocr -g -a cursor -y`
Gemini CLI: `npx skills add YaoApp/yao --skill yao-ocr -g -a gemini-cli -y`

## Description

OCR text recognition expert. ALWAYS invoke this skill when you need to extract text from images or PDFs, including invoices, receipts, ID cards, bank cards, business licenses, tables, handwritten documents, or any visual text content.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# OCR Tools

Two tools for optical character recognition, supporting both VLM-OCR (vision language models) and traditional OCR APIs (Baidu, Google, Azure, PaddleOCR).

## ocr_recognize

Extract text from images or PDF files using OCR.

### Basic usage (plain text output):
```bash
tai tool ocr_recognize --source /path/to/image.png
```

### With URL:
```bash
tai tool ocr_recognize --source https://example.com/document.jpg
```

### Table extraction as Markdown:
```bash
tai tool ocr_recognize --source /path/to/table.png --type table --output_format markdown
```

### Invoice structured extraction:
```bash
tai tool ocr_recognize --source /path/to/invoice.pdf --type invoice --output_format json
```

### With specific provider:
```bash
tai tool ocr_recognize --source /path/to/doc.png --provider baidu
```

### VLM-OCR with custom prompt:
```bash
tai tool ocr_recognize --source /path/to/doc.png --provider llm:qwen-ocr --prompt "只提取表格中的金额列"
```

### PDF page range:
```bash
tai tool ocr_recognize --source /path/to/report.pdf --pages "1-5" --output_format markdown
```

The rest: https://github.com/YaoApp/yao/blob/HEAD/tools/skills/yao-ocr/SKILL.md