Medical Invoice Ocr

v1.1.3

支持识别医疗发票识别。

0· 119·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for scnet-sugon/medical-invoice-ocr.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Medical Invoice Ocr" (scnet-sugon/medical-invoice-ocr) from ClawHub.
Skill page: https://clawhub.ai/scnet-sugon/medical-invoice-ocr
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install medical-invoice-ocr

ClawHub CLI

Package manager switcher

npx clawhub@latest install medical-invoice-ocr
Security Scan
Capability signals
CryptoCan make purchasesRequires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
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.
Assessment
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.

Like a lobster shell, security has layers — review code before you run it.

latestvk9768ch5k83yp72g4az4ats4r184zbgk
119downloads
0stars
13versions
Updated 1w ago
v1.1.3
MIT-0

Sugon-Scnet 医疗发票识别 OCR 技能

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。

功能特性

  • 医疗票据:覆盖医疗发票识别,自动提取关键字段。

前置配置

⚠️ 重要:使用前需要申请 Scnet API Token

申请 API Token

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

配置 Token

手动配置(推荐)

  1. 在技能目录下创建 config/.env 文件,内容如下:
# =====  Sugon-Scnet OCR API 配置 =====
# 申请地址:https://www.scnet.cn
SCNET_API_KEY=your_scnet_api_key_here

# API 基础地址(一般无需修改)
SCNET_API_BASE=https://api.scnet.cn/api/llm/v1
  1. 添加:SCNET_API_KEY=你的密钥
  2. 设置文件权限为 600(仅所有者可读写) ⚠️ 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。

Token 更新

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。

依赖安装

本技能需要 Python 3.6+ 和 requests 库。请运行以下命令:

   pip install requests

使用方法

参数说明

参数名类型必填描述
ocrTypestring识别类型枚举。必须为以下之一:<br>• MEDICAL_INVOICE(医疗发票)
filePathstring待识别图片的本地绝对路径。支持 jpg、png、pdf 等常见格式。

命令行调用示例

   python .claude/skills/medical_invoice_ocr/scripts/main.py MEDICAL_INVOICE /path/to/invoice.jpg

在 AI 对话中使用

用户可以说:

  • “帮我识别这张医疗发票,图片在 /Users/name/Downloads/id.jpg”

AI 会根据 description 中的关键词自动触发本技能。

AI 调用建议

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。 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。

配置选项

编辑 config/.env 文件:

变量名默认值说明
SCNET_API_KEY必需Scnet API 密钥
SCNET_API_BASEhttps://api.scnet.cn/api/llm/v1API 基础地址(一般无需修改)

输出

  • 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。
  • 识别结果位于 data[0].result[0].elements 中,具体字段取决于 ocrType。
  • 错误信息:如果发生错误,会输出以 错误: 开头的友好提示。

注意事项

  • 本技能调用的 OCR API 有 10 QPS 的速率限制。
  • 如果遇到 429 错误,请等待 2-3 秒后重试,不要连续发起请求。
  • 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。

故障排除

问题解决方案
配置文件不存在创建 config/.env 并填入 Token(参考前置配置)
API Key 无效/过期重新申请 Token 并更新 .env 文件
文件不存在检查提供的文件路径是否正确
网络连接失败检查网络连接或防火墙设置
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)
401/403/UnauthorizedToken 无效或过期,重新申请并配置
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。

Comments

Loading comments...