Skip to content
Automation
Skill

/screenshot

Take a screenshot of a URL or the current page

From plugin
firefox-devtools-mcp
4116 skills2 agents
Install
$ npx -y skills add mozilla/firefox-devtools-mcp --skill screenshot --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/screenshot

Context preview

The summary Claude sees to decide when to auto-load this skill.

Take a screenshot of a URL or the current page

SKILL.md

screenshot.SKILL.md
name: screenshot
description: Take a screenshot of a URL or the current page
argument-hint: [url or uid]
disable-model-invocation: true

/firefox-devtools-mcp:screenshot

Captures a screenshot of a URL or the current page and shows it to the user.

Usage

/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

Steps

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"):

  • Call `screenshot_page saveTo="<host-outputs-path>/screenshot.png"` using the host path from the system prompt, not the container path.
  • Load and call `present_files` with that same path so the user receives a clickable file card.

**In Claude.ai chat or Claude Desktop** (no outputs folder in system prompt):

  • Call `screenshot_page` without `saveTo`.
  • Your final response must include the actual image returned — not a description of it. The user cannot see tool call outputs, only what you include in your reply.
Ships withfirefox-devtools-mcp

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.

Get the whole plugin
Stats
414
Stars
61
Forks
Active
Maintenance
TypeScript
Language
20h ago
Last commit
11mo ago
Created

Repo: mozilla/firefox-devtools-mcp

Other skills on firefox-devtools-mcp.