Setup & Installation
openclaw skills install @itsjustfred/playwright-mcp-1-0-0
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install playwright-mcp-1-0-0
What This Skill Does
Browser automation via the Playwright MCP server. Controls Chrome, Firefox, or WebKit to navigate pages, fill forms, click elements, extract data, and capture screenshots. Works headless or headed across Linux, macOS, and Windows.
Exposes Playwright's full browser control through MCP tools, so agents can automate any browser interaction without custom scripts or extra code.
When to use it
- Scraping product prices from e-commerce pages
- Automating login and form submission workflows
- Extracting table data from web dashboards
- Taking screenshots of pages for visual checks
- Testing UI flows without writing test scripts manually
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: extract all rows from the data table at https://example.com/data
AGENT
- 1Call browser_navigate with the target URL
- 2Call browser_evaluate with a script that queries all table rows and returns their text content
- 3Parse the returned JSON array
- 4Return the extracted rows to the user
OUTPUT
Array of table row strings from the page