← Back to Skills Marketplace
TencentCloud General OCR
by
tencent-ocr
· GitHub ↗
· v1.0.2
· MIT-0
595
Downloads
0
Stars
3
Active Installs
3
Versions
Install in OpenClaw
/install tencentcloud-ocr-general
Description
腾讯云广告文字识别(AdvertiseOCR)接口调用技能。当用户需要从图片中识别文字内容时,应使用此技能。支持中英文、横排、竖排及倾斜场景的图片文字识别,支持90度、180度、270度翻转场景的图片识别,返回文本框位置与文字内容。支持图片Base64和URL两种输入方式。
Usage Guidance
This skill's code and documentation implement Tencent Cloud AdvertiseOCR and require your Tencent Cloud API keys (TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY), but the registry metadata does not declare those env vars — treat that as a red flag. Before installing or running: (1) verify the source and trustworthiness of the skill owner; (2) inspect the included scripts (you already have main.py) and confirm there are no unexpected network endpoints; (3) provide credentials only in a controlled environment (use short-lived keys or a restricted account if possible); (4) run the script in an isolated environment (container) and avoid passing files that contain other secrets; (5) consider adding an explicit install step that pins tencentcloud-sdk-python to a known-safe version, or manually install dependencies after review. If you plan to enable this skill for autonomous agent use, resolve the metadata inconsistency first so users understand what credentials will be required.
Capability Analysis
Type: OpenClaw Skill
Name: tencentcloud-ocr-general
Version: 1.0.2
The skill is a legitimate wrapper for the Tencent Cloud AdvertiseOCR API. It uses the official 'tencentcloud-sdk-python' to perform optical character recognition on images provided via URL or local file paths. The code in 'scripts/main.py' correctly handles API credentials through environment variables and contains no evidence of data exfiltration, malicious execution, or prompt injection attacks.
Capability Assessment
Purpose & Capability
The code and SKILL.md implement a Tencent Cloud AdvertiseOCR client and legitimately require Tencent Cloud API keys; the requested capabilities (OCR via tencentcloud-sdk-python) align with the skill's stated purpose. However, the registry metadata claims no required environment variables/credentials while both the instructions and script require TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY — this metadata omission is inconsistent and reduces trust.
Instruction Scope
The runtime instructions and script stay within OCR scope: they accept an image URL or base64/file, read files only when explicitly provided, call the official OCR endpoint (ocr.tencentcloudapi.com), and format the response. The script reads environment variables for credentials and does not access unrelated system paths or exfiltrate data to unexpected endpoints.
Install Mechanism
There is no install spec in the registry (instruction-only), but SKILL.md and the script require the third-party package tencentcloud-sdk-python and instruct the user to pip install it. Lack of an explicit install entry means dependencies won't be auto-installed and package versions are unpinned — this is reasonable for an instruction-only skill but raises supply-chain and reproducibility concerns.
Credentials
The only sensitive items the skill needs are Tencent Cloud API keys (TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY), which are proportionate to calling the Tencent OCR API. The concern is the inconsistency: the registry metadata lists no required env vars while the SKILL.md and script require secrets; that mismatch could lead to accidental credential exposure or user confusion about what will be requested.
Persistence & Privilege
The skill does not request permanent presence, does not set always:true, and does not modify other skills or system-wide configurations. It runs as a standalone script and prints results to stdout.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tencentcloud-ocr-general - After installation, invoke the skill by name or use
/tencentcloud-ocr-general - 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（请求来源标识），用于追踪调用来源，建议统一填写为 Skills
- 其余功能与用法保持不变
v1.0.1
更新显示名称
v1.0.0
Initial release of Tencent Cloud AdvertiseOCR skill.
- Provides OCR text extraction from images, supporting Chinese, English, mixed language, horizontal, vertical, and rotated scenarios.
- Returns detected text, four-point position coordinates, and recognition confidence for each line.
- Supports input via image Base64 string or image URL.
- Includes error code explanations and usage examples.
- Requires `tencentcloud-sdk-python` and Tencent Cloud API credentials via environment variables.
Metadata
Frequently Asked Questions
What is TencentCloud General OCR?
腾讯云广告文字识别(AdvertiseOCR)接口调用技能。当用户需要从图片中识别文字内容时,应使用此技能。支持中英文、横排、竖排及倾斜场景的图片文字识别,支持90度、180度、270度翻转场景的图片识别,返回文本框位置与文字内容。支持图片Base64和URL两种输入方式。 It is an AI Agent Skill for Claude Code / OpenClaw, with 595 downloads so far.
How do I install TencentCloud General OCR?
Run "/install tencentcloud-ocr-general" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TencentCloud General OCR free?
Yes, TencentCloud General OCR is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TencentCloud General OCR support?
TencentCloud General OCR is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TencentCloud General OCR?
It is built and maintained by tencent-ocr (@zt1314p-design); the current version is v1.0.2.
More Skills