Back to list
aktsmm

browser-max-automation

by aktsmm

2🍴 0📅 Jan 24, 2026

SKILL.md


name: browser-max-automation description: Browser automation using Playwright MCP for web testing, UI verification, and form automation. Use when navigating websites, clicking elements, filling forms, taking screenshots, or testing web applications. Supports iframe operations and complex JavaScript execution. license: Complete terms in LICENSE.txt metadata: author: yamapan (https://github.com/aktsmm)

Browser Max Automation

Browser automation via Playwright MCP.

When to use

  • Automating browser-based workflows or QA checks
  • Verifying UI states, DOM changes, or visual regressions
  • Filling forms, clicking elements, or capturing screenshots

Prerequisites

Configure .vscode/mcp.json:

{
  "servers": {
    "playwright": {
      "command": "npx",
      "args": ["@anthropic-ai/mcp-playwright@latest", "--browser", "chrome"]
    }
  }
}

Quick Reference

CommandPurpose
browser_navigateOpen URL
browser_snapshotGet element refs (accessibility tree)
browser_clickClick element by ref
browser_typeInput text
browser_take_screenshotCapture screen
browser_wait_forWait for text/time
browser_run_codeExecute JavaScript

Basic Workflow

1. browser_navigate(url)
2. browser_snapshot → get ref
3. browser_click/type(ref)
4. browser_snapshot → verify

Commands

mcp_playwright_browser_navigate
  url: "https://example.com"

Snapshot

mcp_playwright_browser_snapshot

Returns accessibility tree with ref values for each element.

Click

mcp_playwright_browser_click
  element: "Submit button"
  ref: "f2e123"

Type

mcp_playwright_browser_type
  element: "Username"
  ref: "f2e456"
  text: "user@example.com"
  submit: true  # Press Enter

Screenshot

mcp_playwright_browser_take_screenshot
  filename: "result.png"

Wait

mcp_playwright_browser_wait_for
  text: "Loading complete"  # or
  time: 3

Tabs

mcp_playwright_browser_tabs
  action: "list" | "new" | "close" | "select"
  index: 0

Advanced

iframe Operations

async (page) => {
  const frame1 = page.locator('iframe[name="Content"]').contentFrame();
  const frame2 = frame1.locator('iframe[title="Player"]').contentFrame();
  await frame2.getByRole("radio", { name: "Option A" }).click({ force: true });
  return "Selected";
};

force: true

Use when element is covered by another (e.g., SVG overlay):

await element.click({ force: true });

When browser_run_code is disabled

Use snapshot + click instead:

✅ browser_snapshot → get ref → browser_click(ref)

Reference

TypeUse CaseSelection
radioSingle choiceOne only
checkboxMultiple choice0 to many

Score

Total Score

60/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon