browser-automation
This skill should be used when the user asks about browser automation, testing web pages, extracting content, filling forms, taking screenshots, or monitoring…
Take a screenshot of a URL or the current page
$ npx -y skills add mozilla/firefox-devtools-mcp --skill screenshot --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/screenshotContext preview
The summary Claude sees to decide when to auto-load this skill.
Take a screenshot of a URL or the current page
name: screenshot description: Take a screenshot of a URL or the current page argument-hint: [url or uid] disable-model-invocation: true
Captures a screenshot of a URL or the current page and shows it to the user.
/firefox-devtools-mcp:screenshot https://example.com # Navigate then screenshot /firefox-devtools-mcp:screenshot # Screenshot current page /firefox-devtools-mcp:screenshot <uid> # Screenshot specific element
1. Navigate if a URL was given: call `navigate_page`. 2. Take the screenshot using the method that matches your environment:
**In Cowork** (system prompt contains an outputs folder host path under "Shell access"):
**In Claude.ai chat or Claude Desktop** (no outputs folder in system prompt):
Model Context Protocol server for automating Firefox via WebDriver BiDi (through Selenium WebDriver). Works with Claude Code, Claude Desktop, Cursor, Cline and other MCP clients.
Repo: mozilla/firefox-devtools-mcp
This skill should be used when the user asks about browser automation, testing web pages, extracting content, filling forms, taking screenshots, or monitoring…
Find and fix why a website is slow by capturing and analyzing a Firefox performance profile, or by analyzing a profile the user already has (a saved file or a…