← Back to Skills Marketplace
scnet-sugon

Medical Invoice Ocr

by SCNet-sugon · GitHub ↗ · v1.1.3 · MIT-0
cross-platform ✓ Security Clean
116
Downloads
0
Stars
0
Active Installs
13
Versions
Install in OpenClaw
/install medical-invoice-ocr
Description
支持识别医疗发票识别。
README (SKILL.md)

\r

Sugon-Scnet 医疗发票识别 OCR 技能\r

\r 本技能封装了 Sugon-Scnet 医疗发票识别 OCR 服务,通过单一接口即可调用 1 种识别能力,高效提取文字及票据信息。\r \r

功能特性\r

\r

  • 医疗票据:覆盖医疗发票识别,自动提取关键字段。\r \r

前置配置\r

\r

⚠️ 重要:使用前需要申请 Scnet API Token\r \r

申请 API Token\r

\r

  1. 访问 Scnet 官网 注册/登录\r
  2. 在控制台申请 API 密钥(格式:sc-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx)\r
  3. 复制密钥备用\r \r

配置 Token\r

\r 手动配置(推荐)\r

  1. 在技能目录下创建 config/.env 文件,内容如下:\r
# =====  Sugon-Scnet OCR API 配置 =====\r
# 申请地址:https://www.scnet.cn\r
SCNET_API_KEY=your_scnet_api_key_here\r
\r
# API 基础地址(一般无需修改)\r
SCNET_API_BASE=https://api.scnet.cn/api/llm/v1\r
```\r
2. 添加:`SCNET_API_KEY=你的密钥`\r
3. 设置文件权限为 600(仅所有者可读写)\r
**⚠️ 安全警告**:切勿将 API Key 直接粘贴到聊天对话中,否则可能被记录或泄露。\r
\r
### Token 更新\r
\r
Token 过期后调用会返回 401 或 403 错误。更新方法:重新申请 Token 并替换 config/.env 中的 SCNET_API_KEY。\r
\r
### 依赖安装\r
\r
本技能需要 Python 3.6+ 和 requests 库。请运行以下命令:\r
\r
```bash\r
   pip install requests\r
```\r
---\r
### 使用方法\r
\r
### 参数说明\r
\r
| 参数名 | 类型 | 必填 | 描述 |\r
|--------|------|------|------|\r
| ocrType | string | 是 | 识别类型枚举。必须为以下之一:\x3Cbr>• MEDICAL_INVOICE(医疗发票) |\r
| filePath | string | 是 | 待识别图片的本地绝对路径。支持 jpg、png、pdf 等常见格式。 |\r
\r
### 命令行调用示例\r
\r
```bash\r
   python .claude/skills/medical_invoice_ocr/scripts/main.py MEDICAL_INVOICE /path/to/invoice.jpg\r
```\r
\r
### 在 AI 对话中使用\r
\r
用户可以说:\r
\r
- “帮我识别这张医疗发票,图片在 /Users/name/Downloads/id.jpg”\r
\r
AI 会根据 description 中的关键词自动触发本技能。\r
\r
### AI 调用建议\r
为避免触发 API 速率限制(10 QPS),请串行调用本技能,即等待前一个识别完成后再发起下一个请求。\r
如果使用 OpenClaw 的 exec 工具,建议设置 timeout 或 yieldMs 参数,让命令同步执行,避免多个命令同时运行导致并发。\r
\r
### 配置选项\r
\r
编辑 `config/.env` 文件:\r
\r
| 变量名 | 默认值 | 说明 |\r
|--------|--------|------|\r
| SCNET_API_KEY | 必需 | Scnet API 密钥 |\r
| SCNET_API_BASE | https://api.scnet.cn/api/llm/v1 | API 基础地址(一般无需修改) |\r
\r
### 输出\r
\r
- 标准输出:识别结果的 JSON 数据,结构与 API 文档一致,位于 `data` 字段内。\r
- 识别结果位于 data[0].result[0].elements 中,具体字段取决于 ocrType。\r
- 错误信息:如果发生错误,会输出以 `错误:` 开头的友好提示。\r
\r
### 注意事项\r
\r
- 本技能调用的 OCR API 有 10 QPS 的速率限制。\r
- 如果遇到 429 错误,请等待 2-3 秒后重试,不要连续发起请求。\r
- 建议在调用前确保图片已准备就绪,避免因网络问题导致重复调用。\r
\r
### 故障排除\r
\r
| 问题 | 解决方案 |\r
|------|----------|\r
| 配置文件不存在 | 创建 config/.env 并填入 Token(参考前置配置) |\r
| API Key 无效/过期 | 重新申请 Token 并更新 `.env` 文件 |\r
| 文件不存在 | 检查提供的文件路径是否正确 |\r
| 网络连接失败 | 检查网络连接或防火墙设置 |\r
| 不支持的文件类型 | 确保文件扩展名为允许的类型(参考 API 文档) |\r
| 401/403/Unauthorized | Token 无效或过期,重新申请并配置 |\r
| 429 Too Many Requests | 请求过于频繁,技能会自动等待并重试(最多 3 次)。若持续失败,请降低调用频率或联系服务方提高限额。 |\r
\r
Usage Guidance
This skill appears coherent and does what it claims: it sends a local invoice image to the Sugon-Scnet OCR API and returns structured JSON. Before installing, verify the Scnet service and that you trust its privacy/retention policies (you will send invoice images that may contain personal/medical data). Provide the SCNET_API_KEY via environment variable or a local config/.env file with restricted permissions (chmod 600). Confirm the SCNET_API_BASE URL is correct for your account (default points to api.scnet.cn). Note: repository README contains internal/placeholder links and the skill metadata homepage is a GitHub URL comment — if provenance is important, verify the publisher/source and official project repo before use.
Capability Tags
cryptocan-make-purchasesrequires-sensitive-credentials
Capability Assessment
Purpose & Capability
Name/description, declared dependency (python + requests), required env var (SCNET_API_KEY) and the included script all point to calling the Sugon-Scnet OCR endpoint (https://api.scnet.cn/api/llm/v1/ocr/recognize). The requested resources are proportionate to the stated OCR purpose.
Instruction Scope
SKILL.md and scripts/main.py confine runtime actions to: reading config/.env or SCNET_API_KEY from environment, reading a local image/pdf file, and POSTing it to the Scnet OCR API. There are no instructions to read unrelated system files, other credentials, or to transmit data to unexpected endpoints.
Install Mechanism
There is no install spec (instruction-only packaging plus a small Python script). The only external runtime dependency is the well-known 'requests' Python package — proportional and expected. No downloads from untrusted URLs or archive extraction are present.
Credentials
The skill only requires a single service credential (SCNET_API_KEY) and an optional SCNET_API_BASE; these map directly to the Scnet API usage. The code does not request or access any other unrelated secrets or config paths.
Persistence & Privilege
The skill is not always-enabled, does not modify other skills or global agent settings, and only suggests (but does not automatically write) a local config/.env file. It does not require elevated system privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install medical-invoice-ocr
  3. After installation, invoke the skill by name or use /medical-invoice-ocr
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.3
- 新增 required_env_vars、optional_env_vars 和 primary_credential 字段,明确环境变量要求。 - 版本号从 1.1.2 更新为 1.1.3。 - 其他内容保持不变,无功能逻辑更新。
v1.1.2
- Bumped version to 1.1.2. - No functional or documentation changes in this release.
v1.1.1
medical-invoice-ocr 1.1.1 is a version bump with no code or documentation changes. - Version updated from 1.1.0 to 1.1.1 - No functional changes or file modifications detected
v1.1.0
medical-invoice-ocr 1.1.0 - Version updated from 1.0.9 to 1.1.0. - No file changes detected in this release.
v1.0.9
- Bumped version from 1.0.8 to 1.0.9. - No changes detected in the code or documentation.
v1.0.8
- 支持配置可选环境变量 SCNET_API_BASE,用于自定义 API 基础地址。 - 推荐使用手动方式在 config/.env 文件中配置 SCNET_API_KEY。 - 文档移除了环境变量自动读取说明,强调手动配置流程。 - 版本号更新为 1.0.8。
v1.0.7
medical-invoice-ocr 1.0.7 introduces required environment variable improvements. - 新增 required_env_vars 字段,现需配置 SCNET_API_KEY 和 SCNET_API_SECRET 环境变量 - 设置 primary_credential 字段,主认证参数为 SCNET_API_KEY - 其他功能无变动
v1.0.6
medical-invoice-ocr v1.0.6 - Bumped version to 1.0.6. - No other changes detected from previous version.
v1.0.5
- 支持通过环境变量直接配置 SCNET_API_KEY,提升部署灵活性 - SKILL.md 增加 required_env_vars、optional_env_vars、primary_credential 字段,明确配置项 - 文档中补充环境变量与 .env 文件两种 API Key 配置方式 - 其他使用说明、功能和接口未变
v1.0.4
- Bumped version to 1.0.4. - No user-facing changes; documentation and configuration remain the same.
v1.0.3
- Added skill.yaml for improved skill configuration and metadata. - Clarified API key配置流程,新增安全提示,推荐手动设置 SCNET_API_KEY,避免密钥泄漏。 - 明确依赖 requirements,新增 Python 3 和 requests 安装说明。 - 文档结构优化,补充了环境变量说明及依赖项列表。 - 对用户命令和描述做了提炼,提升易用性和安全性。
v1.0.1
- No changes detected in source files for version 1.0.1. - Documentation remains the same as version 1.0.0.
v0.1.0
Initial release of medical-invoice-ocr skill. - Supports OCR recognition of medical invoices, automatically extracting key fields as structured JSON with confidence scores. - Simple configuration via Scnet API Token, with detailed setup instructions. - Command line and AI conversation usage supported. - Handles image files (jpg, png, pdf, etc.), with error handling and API rate limit guidance included (10 QPS). - Includes troubleshooting and environment configuration instructions.
Metadata
Slug medical-invoice-ocr
Version 1.1.3
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 13
Frequently Asked Questions

What is Medical Invoice Ocr?

支持识别医疗发票识别。 It is an AI Agent Skill for Claude Code / OpenClaw, with 116 downloads so far.

How do I install Medical Invoice Ocr?

Run "/install medical-invoice-ocr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Medical Invoice Ocr free?

Yes, Medical Invoice Ocr is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Medical Invoice Ocr support?

Medical Invoice Ocr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Medical Invoice Ocr?

It is built and maintained by SCNet-sugon (@scnet-sugon); the current version is v1.1.3.

💬 Comments