contentpipe-browser-relay

Activate and verify the OpenClaw Browser Relay Chrome extension via template matching.

10|2|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/PPPPanda/contentPipe --skill contentpipe-browser-relay
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: contentpipe-browser-relay
Source: https://github.com/PPPPanda/contentPipe/tree/main/skills/contentpipe-browser-relay
Command: npx skills add https://github.com/PPPPanda/contentPipe --skill contentpipe-browser-relay

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyautogui, opencv-python, pillow, node, windows-control, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the setup friction of activating and connecting the OpenClaw Browser Relay Chrome extension, which is a prerequisite for ContentPipe’s image generation and related browser-automation steps.

Core Features & Use Cases

  • Chrome window detection and focusing: Ensures the correct Chrome window is in the foreground before any visual matching occurs.
  • Relay icon activation with toggle verification: Finds the relay extension icon (via template matching) and clicks it, then verifies connection by checking the icon badge color.
  • Robust fallbacks and Vision handoff: Retries after reducing icon occlusion, and if template matching fails twice, exits with a VISION_FALLBACK signal plus screenshot paths for downstream Vision localization.
  • Config persistence: Saves last successful icon position and window metadata to improve later activations.

Quick Start

Ask the assistant to run the contentpipe-browser-relay skill to activate and verify the OpenClaw Browser Relay extension connection in the foreground Chrome browser, using template matching first and Vision fallback if needed.

Frequently Asked Questions about contentpipe-browser-relay

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Chrome extension activation for browser automation workflows on Windows?

Automating Chrome extension activation involves locating the extension icon, clicking it to toggle, and verifying connection via badge color analysis. This Skill handles that process using template matching with OpenCV on a visible Chrome window.

What is visual template matching for browser relay connection and how does it work?

Visual template matching for browser relay connection uses OpenCV to find the extension icon on screen, clicks to toggle it, and confirms the connection by analyzing the icon badge color. It retries on failure and provides a Vision fallback.

Do I need pyautogui and OpenCV to automate ContentPipe image generation on WSL?

Yes, you need pyautogui for desktop control and opencv-python for template matching to automate ContentPipe image generation. This setup is required for Windows+WSL environments where Chrome must be foreground and screen-visible.

Why does Chrome need to be in the foreground for relay icon template matching?

Chrome must be in the foreground because template matching relies on visual screen capture to locate the relay extension icon. If the window is occluded or minimized, visual detection fails and triggers a Vision fallback handoff with screenshots.

What happens when template matching fails to find the browser relay icon?

When template matching fails twice, the process retries after reducing icon occlusion. If it still fails, it exits with a VISION_FALLBACK signal and returns screenshot paths for downstream Vision localization to handle the activation.

Can I use this browser relay activation approach for image generation on Linux?

This approach is designed for Windows+WSL setups using pyautogui and windows-control dependencies. It requires a screen-visible Chrome window for visual template matching, making it unsuitable for headless Linux environments without a display.