TencentCloud BizLicense OCR

v1.0.2

腾讯云营业执照识别(BizLicenseOCR)接口调用技能。当用户需要识别营业执照图片上的字段信息(统一社会信用代码、公司名称、主体类型、法定代表人、注册资本、组成形式、成立日期、营业期限、经营范围等)时,应使用此技能。支持图片Base64和URL两种输入方式,支持复印件/翻拍件告警检测、有效期自动拼接、电子营...

0· 345·3 current·3 all-time
bytencent-ocr@zt1314p-design

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zt1314p-design/tencentcloud-ocr-bizlicense.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "TencentCloud BizLicense OCR" (zt1314p-design/tencentcloud-ocr-bizlicense) from ClawHub.
Skill page: https://clawhub.ai/zt1314p-design/tencentcloud-ocr-bizlicense
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

Canonical install target

openclaw skills install zt1314p-design/tencentcloud-ocr-bizlicense

ClawHub CLI

Package manager switcher

npx clawhub@latest install tencentcloud-ocr-bizlicense
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The skill's name, description, SKILL.md, and scripts/main.py all consistently implement a Tencent Cloud BizLicense OCR client. Requiring tencentcloud-sdk-python and Tencent Cloud API credentials is appropriate for this purpose. However, the registry metadata at the top incorrectly lists no required environment variables or primary credential, which is an incoherence between the manifest and what the skill actually needs.
Instruction Scope
SKILL.md and the script narrowly instruct the agent to call Tencent Cloud's BizLicenseOCR via the official SDK, accept either an image URL or a file/Base64 input, and return parsed fields and warnings. The runtime instructions and code only read the provided image file/argument and use the Tencent OCR endpoint; they do not attempt to read unrelated system files or other environment variables.
Install Mechanism
There is no install spec (instruction-only with an included script). The README and code recommend installing tencentcloud-sdk-python via pip. This is a standard package installation and not performed automatically by the skill; no remote download-from-arbitrary-URL or archive extraction is present.
!
Credentials
The script and SKILL.md require TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY (full API keys) which is expected for calling Tencent APIs, but the skill's registry metadata incorrectly declares no required env vars or primary credential. The skill therefore requests high-sensitivity credentials (full API keys) — ensure they are scoped/rotated appropriately and that the manifest is corrected so users know what will be needed.
Persistence & Privilege
The skill does not request always:true, does not attempt to modify other skills or system-wide configuration, and has no install-time persistence. Autonomous invocation is allowed (platform default) but not combined with other high-risk behaviors here.
What to consider before installing
What to consider before installing: - The code is coherent: it will send images to Tencent Cloud's OCR endpoint and requires your Tencent API keys (TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY). The registry metadata incorrectly omits these required env vars — treat that as a red flag about publishing quality. - Only provide credentials if you trust the skill owner; prefer creating a least-privilege, auditable API key for this purpose and rotate/revoke it after use. - Images you pass (via URL or file) will be transmitted to Tencent. Consider privacy/regulatory implications before sending sensitive documents. - The script reads any local file path you pass for --image-base64, so don’t point it at sensitive files you don’t intend to send. - The package asks you to pip install tencentcloud-sdk-python; verify you install that package from a trusted source (PyPI) in an isolated environment. - Because the registry owner and homepage are not provided, consider inspecting the code yourself (done here) or asking the publisher to correct the manifest (declare required env vars) before use.

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

latestvk9769p5rj469krh6m2gvpxz5ed82mqvq
345downloads
0stars
3versions
Updated 1mo ago
v1.0.2
MIT-0

腾讯云营业执照识别 (BizLicenseOCR)

用途

调用腾讯云OCR营业执照识别接口,支持快速精准识别营业执照上的字段,包括统一社会信用代码、公司名称、主体类型、法定代表人、注册资本、组成形式、成立日期、营业期限和经营范围等字段。

核心能力:

  • 基础识别:识别统一社会信用代码(注册号)、公司名称、注册资本、法定代表人、地址、经营范围、主体类型、营业期限、组成形式、成立日期
  • 扩展识别:登记日期、登记机关、标题、编号、重要提示
  • 辅助信息:是否为副本、图片旋转角度、是否有国徽/二维码/印章、是否电子营业执照
  • 告警检测:黑白复印件告警(-9102)、翻拍件告警(-9104)
  • 营业类证件:开启后支持非营业执照的其他营业类证件识别

官方文档:https://cloud.tencent.com/document/api/866/36215

使用时机

当用户提出以下需求时触发此技能:

  • 需要从营业执照图片中提取文字信息
  • 需要获取公司的统一社会信用代码、名称、法定代表人等信息
  • 需要检测营业执照是否为复印件或翻拍件
  • 需要识别电子营业执照
  • 需要识别非营业执照的其他营业类证件(如企业许可证等)
  • 涉及营业执照OCR识别的任何场景

环境要求

  • Python 3.6+
  • 依赖:tencentcloud-sdk-python(通过 pip install tencentcloud-sdk-python 安装)
  • 环境变量:
    • TENCENTCLOUD_SECRET_ID:腾讯云API密钥ID
    • TENCENTCLOUD_SECRET_KEY:腾讯云API密钥Key

使用方式

运行 scripts/main.py 脚本完成营业执照识别。

请求参数

参数类型必填说明
ImageBase64str否(二选一)图片Base64值,编码后不超过7M,支持PNG/JPG/JPEG,不支持GIF
ImageUrlstr否(二选一)图片URL地址,下载时间不超过3秒。都提供时仅使用ImageUrl
EnableCopyWarnbool是否返回告警码(复印件/翻拍件告警),默认false
EnablePeriodCompletebool是否返回自动拼接的有效期,默认true
EnableBusinessCertificatebool是否支持营业类证件识别(含非营业执照证件),默认false
UserAgentstr请求来源标识(可选),用于追踪调用来源,统一固定为Skills

输出格式

识别成功后返回 JSON 格式结果:

标准营业执照识别结果

{
  "RegNum": "91110000MA0XXXXXXX",
  "Name": "XX科技有限公司",
  "Capital": "1000万元人民币",
  "Person": "张三",
  "Address": "北京市海淀区XX路XX号",
  "Business": "技术开发、技术咨询、技术服务...",
  "Type": "有限责任公司(自然人投资或控股)",
  "Period": "2020年01月01日至2040年01月01日",
  "ComposingForm": "",
  "SetDate": "2020年01月01日",
  "IsDuplication": 1,
  "RegistrationDate": "2020年01月01日",
  "Angle": 0.0,
  "NationalEmblem": true,
  "QRCode": true,
  "Seal": true,
  "Title": "营业执照",
  "SerialNumber": "000000000",
  "RegistrationAuthority": "北京市海淀区市场监督管理局",
  "Electronic": false,
  "RequestId": "xxx"
}

含告警信息的结果(需开启 EnableCopyWarn):

{
  "RegNum": "91110000MA0XXXXXXX",
  "Name": "XX科技有限公司",
  "Warnings": [
    {
      "code": -9102,
      "message_id": "WARN_COPY_CARD",
      "description": "黑白复印件告警"
    }
  ],
  "RequestId": "xxx"
}

告警码说明

告警码消息标识含义
-9102WARN_COPY_CARD黑白复印件告警
-9104WARN_RESHOOT_CARD翻拍件告警

错误码说明

错误码描述
FailedOperation.DownLoadError文件下载失败
FailedOperation.ImageDecodeFailed图片解码失败
FailedOperation.NoBizLicense非营业执照
FailedOperation.OcrFailedOCR识别失败
FailedOperation.UnKnowError未知错误
FailedOperation.UnOpenError服务未开通
InvalidParameterValue.InvalidParameterValueLimit参数值错误
LimitExceeded.TooLargeFileError文件内容太大
ResourceUnavailable.InArrears账号已欠费
ResourceUnavailable.ResourcePackageRunOut账号资源包耗尽
ResourcesSoldOut.ChargeStatusException计费状态异常

重要业务逻辑

  1. ImageUrl 优先:ImageBase64 和 ImageUrl 都提供时,仅使用 ImageUrl
  2. 有效期拼接:EnablePeriodComplete 未传入时默认设为 true,自动拼接营业期限
  3. EnableBusinessCertificate 分流逻辑
    • false → 直接走营业执照识别引擎
    • true → 先调用卡证分类模型:
      • 分类为 "BizLicense" → 走原营业执照引擎
      • 分类为 "EnterpriseLicense" → 走文档抽取基础版引擎(BizLicenseNew)
      • 其他类型 → 返回 FailedOperation.NoBizLicense 错误
  4. 电子营业执照:支持识别电子营业执照,通过 Electronic 字段标识
  5. 图片限制:Base64 编码后不超过 7M,支持 PNG/JPG/JPEG,不支持 GIF
  6. 默认请求频率限制:10次/秒

调用示例

# 通过URL识别营业执照
python scripts/main.py --image-url "https://example.com/biz_license.jpg"

# 通过文件路径(自动Base64编码)识别
python scripts/main.py --image-base64 ./biz_license.jpg

# 开启复印件/翻拍件告警检测
python scripts/main.py --image-url "https://example.com/biz_license.jpg" --enable-copy-warn

# 开启营业类证件识别(含非营业执照证件)
python scripts/main.py --image-url "https://example.com/biz_license.jpg" --enable-business-certificate

# 关闭有效期自动拼接
python scripts/main.py --image-url "https://example.com/biz_license.jpg" --enable-period-complete false

# 指定地域
python scripts/main.py --image-url "https://example.com/biz_license.jpg" --region ap-beijing```

Comments

Loading comments...