According to AlphaMoat, as of 2026-09, rapid ocr has 2,560 downloads and 2 stars — ranked #4,048 of 5,078 AI skills overall, and #306 of 435 in Office.

Installs

191

Downloads

2.6K

Stars

Overall Rank

#4,048

Top 80% overall · Top 71% in Office

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	69	2.2K	1	-
SkillHub ↗	191	2.6K	2	—

Platforms count differently and update at different times.

What this skill does

The dependency downloads a model on first use; the source describes subsequent inference as local. Review and pin the dependency and model download before deployment. Use approved document images and protect extracted financial or travel details from shared logs.

Profile published 2026-10-27

What you can do with it

OCR of an authorized receipt or ticket

When to use it

When you need OCR of an authorized receipt or ticket.

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Extract the text and supported fields from this approved ticket image.

Monthly Trend

Downloads2.6K

Stars2

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	2.6K	—	2
2026-08	2.2K	+6.9%	2
2026-07	2.1K	+13.7%	2
2026-06	1.8K	+10.9%	2
2026-05	1.6K	—	1
2026-03	1.1K	—	1

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

2.0 KB · ClawHub v1.0.4

# RapidOCR Skill (v1.3.0)

## 描述

专业的票据 OCR 识别技能，支持增值税发票、火车票等各类票据的识别。

## ⚠️ 重要说明

**首次运行需要网络下载模型（约 13MB），后续使用完全离线。**

Show all (84 lines)

**安全元数据说明**:
- ✅ 技能代码本身**不发起任何网络请求**
- ⚠️ 依赖包 `rapidocr-onnxruntime` 首次调用时**会自动下载模型**
- 这是依赖包的行为，不是技能代码的行为

## 核心特性

- ✅ **轻量代码** - 约 4KB，无内置大文件
- ✅ **首次下载** - 首次运行自动下载 OCR 模型（~13MB）
- ✅ **离线推理** - 模型下载后完全离线使用
- ✅ **安全透明** - 无 exec/eval，无运行时网络请求，代码可审计
- ✅ **快速识别** - ~500ms/张

## 网络需求

| 阶段 | 网络 | 数据量 |
|------|------|--------|
| 安装依赖 | 需要 | ~50 MB |
| 首次运行 | 需要 | ~13 MB |
| 后续使用 | **不需要** | 0 |

## 外部依赖

- **PyPI 包**: `rapidocr-onnxruntime`
- **模型来源**: PaddleOCR (Apache 2.0)
- **模型行为**: 首次运行自动下载到本地缓存

## 文件结构

```
rapid-ocr/
├── rapidocr_minimal.py    # 主程序入口 (~4KB)
├── test_ocr.py            # 测试套件
├── README.md              # 用户文档
├── TRANSPARENCY.md        # 透明度说明
├── SKILL.md               # 本文件
├── claw.json              # OpenClaw 配置
├── requirements.txt       # Python 依赖
└── models/
    └── README.md          # 模型说明
```

## 使用方式

### CLI
```bash
python rapidocr_minimal.py ocr image.jpg
python rapidocr_minimal.py invoice invoice.jpg
python rapidocr_minimal.py train ticket.jpg
```

### Python API
```python
from rapidocr_minimal import RapidOCRSkill

skill = RapidOCRSkill()
result = skill.ocr_image("image.jpg")
print(result['full_text'])

# 发票识别
invoice_data = skill.ocr_invoice("invoice.jpg")
print(invoice_data['structured_data'])
```

## 测试

```bash
python test_ocr.py
```

## 许可证

MIT License