← Back to Skills Marketplace
612
Downloads
1
Stars
4
Active Installs
2
Versions
Install in OpenClaw
/install windows-skills
Description
Windows 桌面自动化技能，支持截图、文字识别(OCR)、图像定位。用于：(1) 截取屏幕内容 (2) 从图片提取文字 (3) 定位UI元素位置进行自动化操作
Usage Guidance
This skill appears to do what it advertises (screenshots, OCR, image-based locating). Before installing: (1) verify you trust the skill source since it will install third-party Python packages via pip; (2) install and verify a local Tesseract binary if you need OCR; (3) be aware the code can simulate mouse clicks and enumerate windows—if you allow the agent to run autonomously it could interact with your desktop, so disable autonomous invocation or test in a sandbox if you are unsure; (4) inspect the Python files yourself or run them in a controlled environment to confirm behavior before granting broader use.
Capability Analysis
Type: OpenClaw Skill
Name: windows-skills
Version: 1.0.1
The skill bundle provides standard Windows desktop automation capabilities, including screenshot capture, OCR text extraction, and image-based UI element localization. The implementation uses well-known libraries (mss, pytesseract, pyautogui, opencv) and standard Windows API calls via ctypes to manage window coordinates, with no evidence of malicious intent, data exfiltration, or unauthorized remote execution.
Capability Assessment
Purpose & Capability
Name/description (screenshots, OCR, image-based UI location) align with included Python modules. The included files implement screenshot capture (mss/ctypes), OCR (pytesseract/Pillow), and image location (OpenCV/pyautogui), all expected for this functionality.
Instruction Scope
SKILL.md instructs installing the listed Python packages and using the provided functions. Runtime instructions only reference screenshot files, Tesseract path, and image templates; they do not read unrelated files, request secrets, or send data to external endpoints.
Install Mechanism
This is an instruction-only skill that recommends pip installing packages (mss, pytesseract, pillow, pyautogui, opencv-python, numpy). Using pip is common but introduces the usual supply-chain considerations (trust the PyPI packages being installed). There is no download-from-URL or archive extraction in the install spec.
Credentials
No credentials or config paths are required. The only environment consideration in code is an optional TESSERACT_CMD env var to locate the local tesseract binary (reasonable for OCR). No unrelated secrets or multiple service tokens are requested.
Persistence & Privilege
Skill is not always-enabled and does not request elevated platform privileges. However, it can perform input actions (pyautogui click) and enumerate windows via Windows APIs—if the agent is allowed to invoke skills autonomously, that ability could control the desktop; consider whether you want autonomous execution enabled.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install windows-skills - After installation, invoke the skill by name or use
/windows-skills - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Added full English documentation alongside the original Chinese instructions.
- Provided English descriptions for all features, usage examples, and dependencies.
- Added an English table describing each script's purpose.
- Updated code examples: clarified parameter names and matching output variables in both languages.
- Improved clarity of usage notes in English section.
- Chinese documentation is preserved and now presented after the English section.
v1.0.0
Initial release of windows-skills.
- Enables Windows desktop automation: screenshot, OCR, and UI element image location.
- Provides scripts for capturing screen/regions/windows, extracting text from images, and locating images on the screen.
- Supports both Chinese and English OCR.
- Includes install instructions and usage notes for accurate results and required dependencies.
Metadata
Frequently Asked Questions
What is Windows Skills?
Windows 桌面自动化技能，支持截图、文字识别(OCR)、图像定位。用于：(1) 截取屏幕内容 (2) 从图片提取文字 (3) 定位UI元素位置进行自动化操作. It is an AI Agent Skill for Claude Code / OpenClaw, with 612 downloads so far.
How do I install Windows Skills?
Run "/install windows-skills" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Windows Skills free?
Yes, Windows Skills is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Windows Skills support?
Windows Skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Windows Skills?
It is built and maintained by civen-cn (@civen-cn); the current version is v1.0.1.
More Skills