playwright-browser-handle-dialog

To accept or dismiss browser dialogs like alert/confirm/prompt, handle the dialog so automation can continue.

⭐6stars🔀3forks📁View on GitHub🕐Updated Jan 7, 2026⬇️2downloads

When & Why to Use This Skill

This Claude skill enables automated interaction with browser-native dialogs such as alerts, confirmations, and prompts using Playwright. It ensures that web automation workflows and browser-based agents can proceed without manual intervention by programmatically accepting or dismissing pop-ups and providing required input text.

Use Cases

  • Automated End-to-End Testing: Automatically handle confirmation dialogs during user journey testing to ensure test suites run to completion without stalling.
  • Robust Web Scraping: Bypass unexpected browser alerts or information pop-ups on legacy websites that would otherwise interrupt data extraction processes.
  • Form Submission Workflows: Programmatically provide necessary responses to browser 'prompt' dialogs during complex multi-step web registrations or data entries.
  • Headless Browser Management: Maintain flow control in headless environments where manual interaction with UI dialogs is impossible.
nameplaywright-browser-handle-dialog
description"To accept or dismiss browser dialogs like alert/confirm/prompt, handle the dialog so automation can continue."

Usage

Use the MCP tool dev-swarm.request to send the payload as a JSON string:

{"server_id":"playwright","tool_name":"browser_handle_dialog","arguments":{}}

Tool Description

Handle a dialog

Arguments Schema

The schema below describes the arguments object in the request payload.

{
  "type": "object",
  "properties": {
    "accept": {
      "type": "boolean",
      "description": "Whether to accept the dialog."
    },
    "promptText": {
      "type": "string",
      "description": "The text of the prompt in case of a prompt dialog."
    }
  },
  "required": [
    "accept"
  ],
  "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>"}}