← Back to Skills Marketplace
TencentCloud LicensePlate OCR
by
tencent-ocr
· GitHub ↗
· v1.0.2
· MIT-0
407
Downloads
0
Stars
2
Active Installs
3
Versions
Install in OpenClaw
/install tencentcloud-ocr-licenseplate
Description
腾讯云车牌识别(LicensePlateOCR)接口调用技能。当用户需要对中国大陆机动车车牌进行自动定位和识别时，应使用此技能。支持返回车牌号码、车牌颜色、置信度和像素坐标信息，支持多车牌场景识别，支持图片Base64和URL两种输入方式。
Usage Guidance
This skill appears to do what it claims (call Tencent Cloud LicensePlateOCR) and requires your Tencent Cloud API keys to operate, but the registry metadata does not list those credentials — that's an inconsistency you should resolve before proceeding. Before installing: (1) confirm the publisher/trustworthiness of the skill (source/homepage are missing), (2) do not supply long-lived root credentials — prefer a minimal-permission API key or short-lived credentials, (3) be aware images (containing license plates) will be uploaded to Tencent Cloud and could have privacy/billing implications, (4) review and test the included scripts locally (scripts/main.py shows the exact calls), and (5) ensure you are comfortable installing the tencentcloud-sdk-python package from PyPI. If you cannot verify the author or the missing registry metadata is not corrected, treat installation as higher risk.
Capability Analysis
Type: OpenClaw Skill
Name: tencentcloud-ocr-licenseplate
Version: 1.0.2
The skill is a standard implementation for calling the Tencent Cloud License Plate OCR API. It uses the official 'tencentcloud-sdk-python' library, follows documented authentication patterns via environment variables, and communicates exclusively with the legitimate Tencent Cloud endpoint (ocr.tencentcloudapi.com). The script 'scripts/main.py' safely handles image inputs via URL or local file paths without any evidence of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, and the included script all align: this is an adapter for Tencent Cloud's LicensePlateOCR and needs Tencent Cloud credentials. However, the skill registry metadata claims no required environment variables or primary credential, which contradicts both SKILL.md and scripts/main.py that explicitly require TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY.
Instruction Scope
SKILL.md and scripts/main.py limit actions to reading an image (file or URL), Base64 encoding if needed, and calling the official Tencent OCR API endpoint (ocr.tencentcloudapi.com). The instructions do not request unrelated files or send data to unexpected endpoints. They do instruct installing the tencentcloud SDK and setting the Tencent Cloud credentials.
Install Mechanism
There is no formal install spec; the instructions and script require the public PyPI package tencentcloud-sdk-python (pip install). Using a PyPI SDK is a common pattern but carries the moderate risk of third-party package supply-chain issues; no arbitrary downloads or unknown URLs are present.
Credentials
The skill legitimately needs Tencent Cloud API keys (TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY) to call the service; that is proportionate to the stated purpose. The concern is the manifest/registry metadata omits these required env vars/primary credential, which is an important omission that could hide required secrets from the installer UI.
Persistence & Privilege
The skill does not request persistent presence (always: false) and does not attempt to modify other skills or global agent configuration. It only runs a client call when invoked.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tencentcloud-ocr-licenseplate - After installation, invoke the skill by name or use
/tencentcloud-ocr-licenseplate - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- 新增可选参数 UserAgent，用于请求来源标识，可设为 Skills 用于追踪调用来源
- 其余功能与接口保持不变
v1.0.1
更新版本和显示名称
v1.0.0
Initial release of Tencent Cloud License Plate OCR skill.
- Provides automatic license plate recognition for Mainland China vehicles.
- Supports detection of multiple plates, plate color, confidence score, and bounding box coordinates.
- Accepts both image Base64 and image URL inputs.
- Returns detailed plate information, including category (e.g., physical or non-physical plate).
- Includes sample usage, error code explanations, and environmental requirements.
Metadata
Frequently Asked Questions
What is TencentCloud LicensePlate OCR?
腾讯云车牌识别(LicensePlateOCR)接口调用技能。当用户需要对中国大陆机动车车牌进行自动定位和识别时，应使用此技能。支持返回车牌号码、车牌颜色、置信度和像素坐标信息，支持多车牌场景识别，支持图片Base64和URL两种输入方式。 It is an AI Agent Skill for Claude Code / OpenClaw, with 407 downloads so far.
How do I install TencentCloud LicensePlate OCR?
Run "/install tencentcloud-ocr-licenseplate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TencentCloud LicensePlate OCR free?
Yes, TencentCloud LicensePlate OCR is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TencentCloud LicensePlate OCR support?
TencentCloud LicensePlate OCR is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TencentCloud LicensePlate OCR?
It is built and maintained by tencent-ocr (@zt1314p-design); the current version is v1.0.2.
More Skills