🌐浏览器自动化 MCP 推荐

MCP (dart-mcp + Marionette) を使ったFlutterアプリのE2E自動化・UI検証ガイド。シミュレーターでのUI動作確認、モックプレビュー検証、Bridge経由のE2Eテスト、スクリーンショット撮影など、アプリの動作検証が必要なときに使う。「動作確認して」「UIを検証して」「E2Eテスト」「シミュレーターで確認」「モックで確認」と言われたときや、UI変更後の検証フェーズで使用すること。

Playwright Browser MCP 与 xterm.js 终端交互方法论。当需要通过浏览器操作网页内嵌终端、CTF 靶场伪终端、Cloud Shell、在线 IDE 中的终端时使用。覆盖终端内容读取（5 种方法）、命令执行、输出捕获、screenshot 降级策略。只要目标页面中有任何形式的 Web 终端（xterm.js/hterm/jQuery Terminal），就应使用此技能

Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

Analisa ROI de automacoes — identifica o que automatizar e quanto vai economizar

Используй только внутри активного Codex Project Autopilot-проекта для automation-задач по его плану; не включай для обычных скриптов вне автопилота.

A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide). Use when user wants to run Cursor agent, code with Cursor, or automate development tasks via Cursor CLI.

10 research automation skills. Trigger: automating experiments, tracking results, reproducible pipelines. Design: ML experiment management, workflow orchestration, and lab automation tools.

Mobile app testing with unit tests, UI automation, performance testing. Use for test infrastructure, E2E tests, testing standards, or encountering test framework setup, device farms, flaky tests, platform-specific test errors.

Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and gives real-time visual feedback. Edit code and refresh to verify fixes live. Use when the user says 'browser pair', 'paired browser', 'let's look at this together', 'open chromium', or wants to iterate on UI with live visual feedback.

Workflow automation, CI/CD pipelines, and task orchestration patterns across platforms like n8n, GitHub Actions, and Make.

Browser automation for testing and verification. Use when you need to interact with web UIs, verify visual changes, fill forms, or capture screenshots.

Automate Docker Hub tasks via Rube MCP (Composio): repositories, images, tags, and container registry management. Always search tools first for current schemas.

One-time setup for a persistent debug browser on `127.0.0.1:9222` for `dev-browser --connect`. Use when browser work is needed but no reusable debug browser is running yet.

Sub-skill of automation: Testing Automation.

Sub-skill of automation: Related Resources.

Sub-skill of automation: n8n Webhook Workflow (+3).

Sub-skill of automation: Low-Code Visual Automation (+2).

Sub-skill of automation: Integration with Workspace-Hub.

Sub-skill of automation: Error Handling (+2).

Sub-skill of automation: Choose n8n when: (+4).

Sub-skill of automation: Best Practices.

Sub-skill of automation: Available Skills.

Sub-skill of automation: Webhook-to-Workflow Pattern (+2).

Control a browser via Chrome DevTools Protocol (CDP) proxy. Use when: (1) navigating to URLs and reading page content, (2) taking screenshots, (3) executing JavaScript in the browser, (4) clicking elements or filling forms, (5) searching and installing Chrome Web Store extensions, (6) interacting with web APIs that require a real browser. NOT for: simple HTTP requests (use curl), local file operations, or when no CDP proxy is available.

Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.

Browser automation. When you need to visit a webpage, open a website, take a screenshot, or perform browser automation, **you MUST read this SKILL.md first** — contains required parameters and operating procedures. **Calling the browser tool without reading may result in failed operations or unexpected behavior.**

Use this skill when you need to design automation testing approaches using patterns like POM, data-driven testing, or BDD; triggers include 自动化测试 and automation testing.

Use this skill when you need to design automation testing approaches using patterns like POM, data-driven testing, or BDD; triggers include automation testing and test automation strategy.

Automation Audit — Skill especializada para auditoria de automação

Design Zapier/Make automation recipes with triggers and actions. Use when building integrations, chaining workflows, configuring triggers, or templating.

Playwright-based browser automation patterns for autonomous web interaction

Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.

Mobile device emulation and responsive testing with Playwright. Use when testing mobile layouts, touch interactions, device-specific features, or responsive breakpoints.

Use this skill whenever the user wants to set up, improve, or run frontend tests (unit, component, and E2E) for a Next.js (App Router) + TypeScript + Tailwind + shadcn/ui project using Vitest/Jest, React Testing Library, and Playwright.

Use this skill when writing or configuring mobile app tests with Detox or Appium, setting up device farms (AWS Device Farm, Firebase Test Lab, BrowserStack), integrating crash reporting (Crashlytics, Sentry, Bugsnag), or distributing beta builds (TestFlight, Firebase App Distribution, App Center). Triggers on mobile e2e testing, native app automation, device matrix testing, crash symbolication, and OTA beta distribution workflows.

Interactive Python REPL automation with common helpers and best practices

Browser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps.

Schedule recurring tasks (cron) and periodic agent check-ins (heartbeat).

Create and manage scheduled and price-triggered automations.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Mobile web testing skill using Playwright device emulation covering responsive testing, touch interactions, viewport management, network throttling, geolocation testing, and mobile-specific UI patterns.

Use when writing new Playwright E2E tests or adding test cases. Provides testing philosophy, patterns, and best practices from the Playwright Developer Handbook.

Help Somi turn repeated work into safe automations with clear operator visibility.

Governance-first architect for business automations (n8n-first) who audits value, risk, and maintainability before implementation.

Zapier Recipe Book. Use when you need zapier recipe capabilities. Triggers on: zapier recipe.

Executes approved shell commands, manages backups, and safely retrieves secrets from Bitwarden.

Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.

Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.