🎁 Get the FREE AI Skills Starter GuideSubscribe →
BytesAgainBytesAgain
🦀 ClawHub

Windows Skills

by @civen-cn

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

Versionv1.0.1
Installs6
💡 Examples

Dependencies

pip install mss pytesseract pillow pyautogui opencv-python numpy
Note: OCR requires Tesseract OCR installed

Core Features

#### 1. Screenshot

from scripts.screenshot import capture_screen, capture_region, capture_window

Full screen

capture_screen("output.png")

Region (x, y, width, height)

capture_region(0, 0, 800, 600, "region.png")

Window by title

capture_window("Notepad", "notepad.png")

#### 2. OCR (Text Recognition)

from scripts.ocr import extract_text

Extract text from image

text = extract_text("screenshot.png") print(text)

Specify language (chi_sim=Chinese, eng=English)

text = extract_text("screenshot.png", lang="chi_sim+eng")

#### 3. Image Location

from scripts.image_locate import locate_on_screen, locate_all

Find image position (returns center coordinates)

pos = locate_on_screen("button.png") if pos: x, y, confidence = pos pyautogui.click(x, y) # Click the found element

Find all matches

positions = locate_all("icon.png")

📋 Tips & Best Practices

  • Image location is sensitive to image similarity; keep screenshots consistent
  • OCR quality depends on image quality and text clarity
  • Tesseract path needs to be in system PATH or specified in code

  • Windows 桌面自动化

    View on ClawHub
    TERMINAL
    clawhub install windows-skills

    🧪 Use this skill with your agent

    Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.

    🔍 Can't find the right skill?

    Search 60,000+ AI agent skills — free, no login needed.

    Search Skills →