playwright-browser-run-code
To run a custom Playwright script on the page, execute a code snippet for advanced interactions.
When & Why to Use This Skill
The playwright-browser-run-code skill empowers Claude to execute custom JavaScript snippets via the Playwright framework for sophisticated web browser control. It bridges the gap between simple navigation and complex web interactions, allowing for programmable automation of dynamic web pages, element manipulation, and advanced data extraction that standard tools cannot handle.
Use Cases
- Automating complex, multi-step workflows on web applications that require specific timing, conditional logic, or custom event triggers.
- Performing advanced web scraping and data extraction from modern, single-page applications (SPAs) or sites with heavily obfuscated DOM structures.
- Executing automated UI/UX regression tests by simulating precise user behaviors such as drag-and-drop, hover states, and keyboard shortcuts.
- Generating dynamic reports or capturing specific page states by interacting with web-based dashboards before taking screenshots or extracting values.
| name | playwright-browser-run-code |
|---|---|
| description | "To run a custom Playwright script on the page, execute a code snippet for advanced interactions." |
Usage
Use the MCP tool dev-swarm.request to send the payload as a JSON string:
{"server_id":"playwright","tool_name":"browser_run_code","arguments":{}}
Tool Description
Run Playwright code snippet
Arguments Schema
The schema below describes the arguments object in the request payload.
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: `async (page) => { await page.getByRole('button', { name: 'Submit' }).click(); return await page.title(); }`"
}
},
"required": [
"code"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
Background Tasks
If the tool returns a task id, poll the task status via the MCP request tool:
{"server_id":"playwright","method":"tasks/status","params":{"task_id":"<task_id>"}}