- name
- manual-automation
- description
- Manual browser testing and automation using Chrome DevTools MCP server. Handles port management, app launch, browser automation, login, and end-to-end testing.
- metadata
- version: 1.0.0
Manual Browser Automation
This skill enables manual browser testing and automation using the Chrome DevTools MCP server. It orchestrates the full workflow from port management through application launch, browser automation, login, and end-to-end testing.
Workflow Execution Steps
1. Port Management
Check if port 3000 is free:
lsof -i :3000
If port is in use:
- Identify the process using the port
- Stop the existing application gracefully
- Verify the port is now free
If port is free:
- Proceed to application launch
2. Application Launch
Launch the application in terminal:
- Start the application server on port 3000
- Run in background mode to allow continued agent execution
- Monitor startup logs to ensure successful initialization
- Wait for the application to be ready (health check or expected log message)
3. Browser Automation Setup
Initialize Chrome DevTools MCP connection:
- Use MCP tools to connect to the browser
- Navigate to
http://localhost:3000 - Wait for page load completion
- Take initial screenshot for documentation
4. Login Flow
Execute login sequence:
- Locate login form elements using MCP selectors
- Fill in credentials (use environment variables or secure storage)
- Submit the login form
- Wait for successful login redirect
- Verify login state (check for expected UI elements or cookies)
- Take screenshot of logged-in state
5. Testing Execution
Perform end-to-end tests using MCP tools:
Available MCP tool categories:
- Input automation:
click,type_text,fill, , , , , , ,