invoice-qr-scanner

# Invoice QR Scanner

## Overview

This skill enables automatic electronic invoice application by scanning QR codes from receipt images and filling out online invoice forms. It handles the complete workflow from QR code detection to invoice submission.

## Workflow

### Step 1: QR Code Recognition

When a user provides an invoice receipt image containing a QR code:

1. Run the QR code recognition script:
   ```bash
   node scan-qr.js <image-path>
   ```
2. The script outputs the decoded QR code URL
3. If recognition fails, ask user to provide the URL directly

### Step 2: Navigate to Invoice System

1. Open the decoded URL in browser automation
2. Verify the page loads successfully
3. Take snapshot to understand form structure

### Step 3: Retrieve Company Information

Before filling the form, retrieve the user's company information:

1. Check memory files for stored invoice header information:
   - Search `memory/YYYY-MM-DD.md` for recent invoice info
   - Check `MEMORY.md` for long-term stored details
2. Required fields typically include:
   - Company name (公司名称)
   - Tax ID/Unified Social Credit Code (税号)
   - Address (地址)
   - Phone number (电话)
   - Bank name (开户行)
   - Bank account number (银行账号)

### Step 4: Fill Invoice Form

1. Analyze the form structure using browser snapshot
2. Fill in company information fields
3. Fill in recipient information:
   - Phone number (手机号)
   - Email address (邮箱)
4. Verify all required fields are completed

### Step 5: Review and Submit

1. Submit the form
2. Review confirmation page
3. Verify all information is correct
4. Report results to user

## Error Handling

### QR Code Not Recognized

If QR code recognition fails:
1. Ask user to provide the URL directly
2. Suggest using phone to scan and share the URL

### Form Structure Changes

If the invoice system form structure changes:
1. Take a new snapshot
2. Identify updated field references
3. Adapt the filling process accordingly
4. Document the new stru...

# Invoice QR Scanner Skill

## Description

自动扫描发票收据中的二维码并填写电子发票申请的开票助手。

## Features

- ✅ **QR码识别**：使用Node.js + qrcode-reader库自动识别图片中的二维码
- ✅ **智能填充**：利用系统自动完成功能提高准确性
- ✅ **内存集成**：自动从MEMORY.md读取公司和联系信息
- ✅ **完整流程**：从识别到提交的完整开票流程
- ✅ **错误处理**：清晰的异常处理和备选方案

## Installation

克隆GitHub仓库即可使用：

```bash
git clone https://github.com/chenzhuowen/invoice-qr-scanner.git
cd invoice-qr-scanner
```

## Requirements

### System Requirements
- OpenClaw环境
- Node.js v14+
- 浏览器自动化工具

### NPM Dependencies

```bash
npm install qrcode-reader canvas
```

或者使用skill中的package.json：
```bash
cd invoice-qr-scanner/scripts
npm install
```

## Usage

### 1. 扫描二维码

```bash
node scan-qr.js <path-to-receipt-image>
```

**示例：**
```bash
node scan-qr.js /path/to/receipt.jpg
```

**输出：**
```
✅ 识别成功: https://fpkj.vpiaotong.com/tp/scan/index/...
```

### 2. 使用Skill

当用户要求扫描发票二维码时，OpenClaw会自动加载这个skill并执行以下操作：

1. 识别图片中的QR码
2. 打开开票系统URL
3. 从MEMORY.md读取公司信息
4. 填写开票申请表单
5. 确认并提交

## Configuration

### Memory Integration

此skill依赖于以下MEMORY.md中的信息：

**公司信息：**
- Company name（公司名称）
- Tax ID（税号）
- Address（地址）
- Phone number（电话）
- Bank name（开户行）
- Bank account number（银行账号）

**联系信息：**
- Mobile phone numbers（手机号）
- Email addresses（邮箱）

当填写表单时，skill会自动从MEMORY.md读取这些信息。

## Workflow

```
┌─────────────┐
│ 1. QR识别  │ → 使用qrcode-reader扫描图片
└─────────────┘
       ↓
┌─────────────┐
│ 2. 进入系统  │ → 浏览器打开URL
└─────────────┘
       ↓
┌─────────────┐
│ 3. 信息检索  │ → 从MEMORY.md读取
└─────────────┘
       ↓
┌─────────────┐
│ 4. 填写表单  │ → 自动填充+利用自动完成
└─────────────┘
       ↓
┌─────────────┐
│ 5. 确认提交  │ → 核对并提交
└─────────────┘
```

## File Structure

```
invoice-qr-scanner/
├── SKILL.md...