Enhance webpage-snapshot plugin with explicit wait handling

[Copilot]

PR #2 added the webpage-snapshot plugin infrastructure but the command definition lacked explicit page load handling, risking incomplete screenshots.

Changes

• Added playwright-browser_wait_for to allowed-tools - Enables proper wait handling after navigation
• Specified exact tool usage in steps - Each step now references the specific playwright tool to use (playwright-browser_navigate, playwright-browser_wait_for, playwright-browser_take_screenshot, playwright-browser_close)
• Defined screenshot naming convention - Filenames should include domain + timestamp for traceability
• Added explicit error handling requirements - Command now requires clear error messages when page load fails

Command Structure

## Steps

1. Navigate to the URL provided by the user
2. Wait for the page to load completely using `playwright-browser_wait_for` (wait at least 2-3 seconds after navigation)
3. Take a screenshot of the page using `playwright-browser_take_screenshot`
4. Save the screenshot with an appropriate filename (e.g., including domain and timestamp)
5. Close the browser when done using `playwright-browser_close`

The changes ensure reliable webpage captures with proper resource cleanup.

Original prompt

拉取请求: #2

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.