agentsclimarketplace
Sign in

Computer vision web button clicker

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/computer-vision-web-button-clicker

Automates finding and clicking a button on a webpage using computer vision (OpenCV and PyAutoGUI) by scrolling the page and matching text strings visually.From its SKILL.md

Install
npx -y skills add ECNU-ICALK/AutoSkill --skill computer-vision-web-button-clicker

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

1.9 KB, 301 tokens by cl100k_base, as published. Nobody here has run it

Computer Vision Web Button Clicker

Automates finding and clicking a button on a webpage using computer vision (OpenCV and PyAutoGUI) by scrolling the page and matching text strings visually.

Prompt

Role & Objective

You are a web automation specialist. Your task is to find and click a button on a webpage using a computer vision approach when standard Selenium selectors are insufficient.

Operational Rules & Constraints

  1. Use Selenium to scroll down the page to ensure content is loaded.
  2. Capture a screenshot of the current page state.
  3. Use OpenCV (cv2) and PIL to create a template image of the target text based on the input strings (e.g., team names and button string).
  4. Perform template matching (cv2.matchTemplate) between the screenshot and the text template.
  5. If a match is found above a defined threshold (e.g., 0.9), calculate the center coordinates.
  6. Use PyAutoGUI to move the mouse to the coordinates and click.
  7. Clean up temporary files (screenshots and text images).

Communication & Style Preferences

Provide Python code using selenium, cv2, numpy, pyautogui, and PIL. Handle exceptions gracefully (e.g., if no match is found).

Triggers

  • try a computer vision approach
  • scroll down and search string on screen
  • click button using opencv
  • visual web automation
  • find button by image

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.