メニュー
Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | playwright-mcp |
| description | Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows. |
| metadata | {"openclaw":{"emoji":"🎭","os":["linux","darwin","win32"],"requires":{"bins":["playwright-mcp","npx"]},"install":[{"id":"npm-playwright-mcp","kind":"npm","package":"@playwright/mcp","bins":["playwright-mcp"],"label":"Install Playwright MCP"}]}} |
Browser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically.
npm install -g @playwright/mcp
# Or
npx @playwright/mcp
Install browsers (first time):
npx playwright install chromium
npx @playwright/mcp
# Headless mode
npx @playwright/mcp --headless
# Specific browser
npx @playwright/mcp --browser firefox
# With viewport
npx @playwright/mcp --viewport-size 1280x720
# Ignore HTTPS errors
npx @playwright/mcp --ignore-https-errors
# MCP tools available:
# - browser_navigate: Open URL
# - browser_click: Click element
# - browser_type: Type text
# - browser_select_option: Select dropdown
# - browser_get_text: Extract text content
# - browser_evaluate: Run JavaScript
# - browser_snapshot: Get page structure
# - browser_close: Close browser
1. browser_navigate to form URL
2. browser_type into input fields
3. browser_click to submit
4. browser_get_text to verify result
1. browser_navigate to page
2. browser_evaluate to run extraction script
3. Parse returned JSON data
| Tool | Description |
|---|---|
browser_navigate | Navigate to URL |
browser_click | Click element by selector |
browser_type | Type text into input |
browser_select_option | Select dropdown option |
browser_get_text | Get text content |
browser_evaluate | Execute JavaScript |
browser_snapshot | Get accessible page snapshot |
browser_close | Close browser context |
browser_choose_file | Upload file |
browser_press | Press keyboard key |
# Security
--allowed-hosts example.com,api.example.com
--blocked-origins malicious.com
--ignore-https-errors
# Browser settings
--browser chromium|firefox|webkit
--headless
--viewport-size 1920x1080
--user-agent "Custom Agent"
# Timeouts
--timeout-action 10000 # Action timeout (ms)
--timeout-navigation 30000 # Navigation timeout (ms)
# Output
--output-dir ./playwright-output
--save-trace
--save-video 1280x720
browser_navigate: { url: "https://example.com/login" }
browser_type: { selector: "#username", text: "user" }
browser_type: { selector: "#password", text: "pass" }
browser_click: { selector: "#submit" }
browser_get_text: { selector: ".welcome-message" }
browser_navigate: { url: "https://example.com/data" }
browser_evaluate: {
script: "() => { return Array.from(document.querySelectorAll('table tr')).map(r => r.textContent); }"
}
browser_navigate: { url: "https://example.com" }
browser_evaluate: { script: "() => { document.body.style.zoom = 1; return true; }" }
# Screenshot saved via --output-dir or returned in response
--no-sandbox with caution)# Update browsers
npx playwright install chromium
# Debug mode
npx @playwright/mcp --headless=false --output-mode=stdout
# Check installation
playwright-mcp --version
Process raw events into distilled long-term memories using batch processing.
Create a brand-new reusable skill from a single completed task. Read the per-task SKILL_SOURCE markdown the handler wrote, distil the workflow into a generalised SKILL.md, save it at skills/<name>/SKILL.md. Use this when CraftBot has spawned a 'Create Skill' workflow task and you need to author the new skill end-to-end without user interaction.
Refine an existing CraftBot skill using evidence from one completed task that used it. Read the per-task SKILL_SOURCE markdown the handler wrote, diff it against the existing SKILL.md, apply surgical edits to skills/<target>/SKILL.md. Use this when CraftBot has spawned an 'Improve Skill' workflow task and you need to refine the skill's accuracy or token efficiency without redesigning it.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Conduct a conversational interview to explore user's job and life goals
Daily planning skill that reviews recent interactions, scans external environment, identifies tasks for today, and updates the Goals, Plan, and Status section in PROACTIVE.md.