| name | Playwright Chrome Browser |
| description | Enable browser automation capabilities using Playwright MCP server. This allows agents to interact with web pages, take screenshots, fill forms, and perform automated browser tasks through the Playwright automation framework. |
| version | 1.0.0 |
| category | automation |
| skillType | mcp |
| triggers | ["playwright","browser","web automation","screenshot","click","fill form","navigate","headless"] |
| tags | ["browser","automation","playwright","mcp","web","headless","testing"] |
| execution | {"type":"mcp-tool","mcpTool":{"toolName":"mcp__playwright__*","defaultParams":null}} |
| runtime | {"runtime":"claude-code","requiredMcpServers":["@playwright/mcp"]} |
| notices | [{"type":"requirement","message":"This skill requires the Playwright MCP server. Crewly auto-configures this when browser automation is enabled in Settings. Manual install: npx @playwright/mcp@latest"},{"type":"info","message":"This skill is only available when using Claude Code as the AI runtime."},{"type":"info","message":"Playwright runs in headless mode by default. The browser window is not visible during automation."}] |
Playwright Chrome Browser
This skill enables browser automation capabilities through the Playwright MCP server for Claude Code.
Prerequisites
Crewly auto-configures the Playwright MCP server when browser automation is enabled in Settings (enableBrowserAutomation: true). The .mcp.json file is generated automatically during agent startup.
For manual installation:
npx @playwright/mcp@latest
Capabilities
When this skill is enabled, agents can:
- Navigate to web pages
- Take screenshots of pages or specific elements
- Fill out forms and input fields
- Click buttons and links
- Extract text content from pages
- Wait for elements to appear
- Handle multiple browser tabs
- Execute in headless mode (no visible browser window)
Usage
The browser automation tools are available through MCP (Model Context Protocol) when the Playwright MCP server is configured in Claude Code.
Available Tools
mcp__playwright__browser_navigate - Navigate to a URLmcp__playwright__browser_screenshot - Take a screenshotmcp__playwright__browser_click - Click on an elementmcp__playwright__browser_fill - Fill an input fieldmcp__playwright__browser_select - Select from dropdownmcp__playwright__browser_hover - Hover over an elementmcp__playwright__browser_evaluate - Execute JavaScript on the pagemcp__playwright__browser_console_messages - Get console messagesmcp__playwright__browser_network_requests - Monitor network activitymcp__playwright__browser_tab_list - List open tabsmcp__playwright__browser_tab_new - Open a new tabmcp__playwright__browser_tab_select - Switch between tabsmcp__playwright__browser_tab_close - Close a tabmcp__playwright__browser_close - Close the browser
Comparison with Chrome Browser Skill
