Business License Ocr

v1.0.4

精准识别中国大陆本营业执照。自动提取统一社会信用代码、企业名称、法定代表人、注册资本、成立日期、经营范围、住所等信息。

0· 174·0 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/business-license-ocr.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Business License Ocr" (scnet-sugon/business-license-ocr) from ClawHub.
Skill page: https://clawhub.ai/scnet-sugon/business-license-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 business-license-ocr

ClawHub CLI

Package manager switcher

npx clawhub@latest install business-license-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
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (business license OCR) match the implemented behavior: the Python script uploads a local file to https://api.scnet.cn/api/llm/v1/ocr/recognize and prints structured JSON. Requiring SCNET_API_KEY/SCNET_API_BASE is appropriate. Minor metadata mismatch: the registry summary at the top claimed 'Required env vars: none', but both SKILL.md and skill.yaml correctly declare SCNET_API_KEY (primary credential). This appears to be an artefact of registry extraction, not a functional mismatch.
Instruction Scope
SKILL.md and scripts only ask the agent to read a local image path and a local config/.env (or environment variable) and then call the Scnet OCR API — scope is limited to OCR. Small scope-creep items: usage examples mention identifying ID cards and invoices even though the script's usage text and documentation focus on BUSINESS_LICENSE (the code accepts a generic ocrType but CLI help suggests BUSINESS_LICENSE). This is a documentation inconsistency but not evidence of hidden behavior. The SKILL.md also instructs creating config/.env and warns not to paste API keys into chat (good).
Install Mechanism
No install spec is provided; the skill ships a small Python script and expects python3 + requests. Nothing is downloaded from arbitrary URLs or executed from remote archives. This is low-risk for installation.
Credentials
Only SCNET_API_KEY (and optional SCNET_API_BASE) are required to operate, which is proportional for a cloud OCR wrapper. The script reads config/.env under its own skill directory — it does not request unrelated credentials or other system config paths.
Persistence & Privilege
always: false and disable-model-invocation left default (normal). The skill does not request permanent system-wide privileges, does not modify other skills, and does not persist tokens outside its own config/.env file. No elevated privileges requested.
Assessment
This skill is a thin wrapper around the Scnet OCR API and requires you to provide an SCNET_API_KEY (stored in config/.env or an environment variable). Before installing: 1) confirm you trust the Scnet service (https://www.scnet.cn) and understand that image data will be uploaded to that service; 2) store the API key in a file with restricted permissions (the README recommends chmod 600) or use environment variables; 3) note the small documentation inconsistency where example usage mentions other document types — double-check the ocrType you pass. If you don't want files uploaded to an external service, do not install/use this skill.

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

latestvk97ch19wqykr8t4qyghtkyp5hs84w1a0
174downloads
0stars
4versions
Updated 1w ago
v1.0.4
MIT-0

Sugon-Scnet 营业执照 OCR 技能

本技能封装了 Sugon-Scnet 营业执照 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

  • 行业资质:识别营业执照(统一社会信用代码、企业名称等)。

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>• BUSINESS_LICENSE(营业执照)
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/sugon-scnet-ocr/scripts/main.py BUSINESS_LICENSE /path/to/invoice.jpg

在 AI 对话中使用

用户可以说:

  • “帮我识别这张身份证,图片在 /Users/name/Downloads/id.jpg”
  • “提取这张发票的信息,路径是 /Users/name/Downloads/fapiao.png”
  • “OCR 这个图片里的文字,图片在 /Users/name/Desktop/text.png”

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...