🌐浏览器自动化 MCP 推荐

Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.

Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover/extract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR/fetch surface for client integration.

Front door for agent automation — decide the SHAPE (Workflow vs ATM vs skill), then hand off. Triggers: "build automation", "convert skills to workflows", "which shape".

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Use this skill when the user asks the agent to open, browse, inspect, extract content from, click through, fill forms on, screenshot, or verify a web page with a browser. Also use it for MoviePilot scenarios that need browser interaction, such as checking a site page, confirming a JavaScript-rendered result, testing login state, capturing visible errors, or updating and validating tracker site cookies.

Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP database services, Infrastructure as Code, high availability, disaster recovery, performance optimization, and compliance. Handles multi-cloud strategies, container databases, and cost optimization. Use PROACTIVELY for database architecture, operations, or reliability engineering.

Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.

Direct browser control via CDP — automate, scrape, test, or interact with web pages by driving the user's already-running Chrome (or a Browser Use cloud browser). Use when the user wants to click, screenshot, fill forms, extract data, or navigate real web pages. Default to screenshots + coordinate clicks, not selector hunting. Requires the one-time `browser-harness` CLI install (see references/install.md).

Testing CKEditor 5 plugins in the Trilium monorepo. Use when adding or reviewing unit tests for a packages/ckeditor5-* package, debugging a failing test, or setting up a package's test runner. Covers the two Vitest environments Trilium uses (happy-dom and the WebdriverIO browser mode), the per-package vitest.config.ts, testing against a real ClassicEditor, the model/view helpers imported from 'ckeditor5' (_setModelData / _getModelData / _getViewData and their {}/[] selection syntax), vi spies/mocks, idiomatic patterns for schema/conversion/command/UI tests, the pnpm --filter runner, and Trilium-specific conventions and gotchas. Complements the ckeditor5-plugin-development and writing-unit-tests skills.

Use when the user wants a hands-free loop where grabbing UI elements in the browser with React Grab feeds tasks to the agent automatically, with no copy-paste or manual handoff. Triggers: "watch react grab", "monitor my grabs", "auto-process react grab", "watch my clipboard for grabs". Not for a one-off paste of a single grab; this is the continuous, always-on loop.

Migra workflows de n8n/Make al ecosistema Claude Code. Analiza JSONs, mapea nodos, propone implementacion (skills, crons, web apps, dashboards) y detecta mejoras. Usa cuando el usuario pegue un JSON de n8n o mencione migrar automatizaciones.

Crea, valida y despliega workflows de n8n desde Claude Code usando el MCP n8n-mcp. Úsala cuando el usuario diga "crea un workflow en n8n", "monta un n8n que haga X", "convierte esta idea en automatización", "diseña un flujo n8n", o describa una secuencia de pasos automatizables (recibir webhook → procesar → enviar a Slack, scheduler diario que lee de Google Sheets, etc.). Activable también con frases como "auto­matización", "n8n", "workflow", "trigger". NO uses esta skill para migrar workflows existentes de n8n a Claude — para eso usa automation-n8n-to-claude.

Automationen und Monitoring: Entwirft Monitore für Datenraum-Neuzugaenge, Q&A-Status, CP-Deadlines, Registerupdates, MAR-Signale und PMI-Aufgaben im Corporate/M&A-Kontext. Normen: MAR Art. 17, § 41 GWB (Vollzugsverbot), § 56 AWV.

Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.

Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.

Motor de Loop Engineering. Convierte trabajo repetitivo en sistemas: se diseñan UNA vez y se ejecutan N veces con verificación, compuertas humanas y aprendizaje acumulado (REGLAS.md). Tres funciones: (1) INSTALACIÓN — en el primer uso, entrevista de 5 preguntas para personalizar la skill al negocio, herramientas y límites de cada usuario; (2) RADAR — detectar cuándo una tarea se está convirtiendo en loop y preguntar «¿Lo diseñamos o lo disparo?»; (3) FÁBRICA — diseñar el loop (canvas de 9 campos), dispararlo, operarlo y evaluarlo. Usar siempre que el usuario diga "loop", "sistematiza esto", "automatiza este proceso", "línea de producción", "todas las semanas", "para cada cliente", "hazlo en lote", "diseña el sistema", "diseña el loop", "monta el sistema de", "deja de hacerlo a mano", "loop engineering", "convierte esto en un sistema", "configura la skill de loops", o pida repetir una tarea ya hecha 2+ veces en la conversación. Activar proactivamente (modo RADAR) a la 3ª repetición de una misma tarea con estru

Manage SOP templates, scheduled automation tasks, and run history through AI-callable tools.

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.

GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task beyond simple git commands.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.

Shared workflow for browser-based review of user-visible frontend changes in Langfuse. Use when a change affects UI behavior, layout, styling, navigation, or browser-visible regressions and should be checked with the Playwright MCP server before signoff.

Wire a nao project's context folder to a remote nao instance (Cloud or self-hosted) so every push to `main` automatically runs `nao deploy` via GitHub Actions. Use when the user has a working local nao project versioned in Git and wants their team's deployed instance to always reflect the latest committed context. Covers `nao deploy` usage, the GitHub Actions workflow, organization API keys, GitHub Secrets, `.naoignore`, environment-variable references in `nao_config.yaml`, and create-vs-update behavior. Do not use for first-time project setup (use `setup-context`) or for `nao sync` automation that commits warehouse metadata back to the repo (covered in the docs' synchronization page).

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

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking buttons, taking screenshots, extracting page data, reading selected Open Design browser-tab context, testing web apps, dogfooding Open Design previews, QA, bug hunts, or reviewing app quality. Prefer local Open Design preview URLs unless the user explicitly asks for external browsing.

Automation Governance skill for the OpenCode ecosystem

Existing Chrome automation: Chrome plugin first, mcporter fallback.

Run automation loop hardening.

Use when turning repeated manual operations into safer, observable, reusable automation loops. Triggers:

Converts a PDF into one self-contained, readable HTML file that preserves images, tables, charts and reading order — optionally translating it into another language while keeping every figure. Uses structured extraction (PyMuPDF), font-size-driven layout, compressed base64-inlined images (a single portable file), and mandatory headless-Chrome visual verification. Use whenever someone wants to READ a PDF as a web page or clean document, turn a PDF into HTML, or translate a PDF into another language while keeping its images/tables/charts intact — e.g. "PDF 转 HTML", "把这个 PDF 转成中文网页版", "make this report readable", "translate this PDF but don't lose the charts", "I just want to read this PDF on my phone". Distinct from doc-to-markdown (plain Markdown text) and pdf-creator (Markdown→PDF) — this one produces a styled, image-faithful HTML reading experience.

Convert markdown files to professional PDF documents with proper Chinese font support, theme system, and visual self-check. Use whenever the user asks to create PDFs, convert markdown to PDF, generate printable documents, or needs documents formatted for print or mobile reading. This skill MUST be used instead of manual pandoc/Chrome invocations — it handles CJK typography, Chrome header/footer suppression, and mandatory visual verification that manual approaches miss. **Scope — markdown → PDF only.** For Word (.docx) output use `minimax-docx`; this skill does not produce docx and the two pipelines are intentionally orthogonal.

Use when opening, inspecting, clicking, filling, snapshotting, or otherwise automating web pages for this repo, including local dev servers and browser-based verification.

Event-triggered and schedule-triggered automations with natural-language conditions. Use when creating automations, wiring events, or understanding how triggers fire.

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.

Testing practices for this monorepo — choosing between unit and end-to-end tests, where test files live, how tsconfig.test.json fits in, how to drive Playwright, to to write/adapt UI/end-to-end tests, and which test runner (vitest vs jest) to use. MUST be invoked BEFORE any code search or file reads whenever the user asks to add, write, or extend a test, add coverage, create a test file, set up testing in a new package, mentions vitest/jest, or refers to an existing `*.test.ts` file. Applies equally to unit tests and to end-to-end / UI tests — the skill routes to a Playwright-MCP-first discovery flow for the latter, which differs from normal code-search workflow.

Inspect UI via cursor-ide-browser (Cursor Browser tab); fall back to user-playwright if internal browser MCP is unavailable. Use for @Browser, open tab, layout checks, localhost — or when user explicitly asks for Playwright.

Write step-by-step automation instructions for a workflow, tailored to your tool (Claude, n8n or Zapier). Best run right after discover-patterns or process-analyst.

Automation YAML patterns, triggers, conditions, actions, and best practices for Home Assistant.

Local OpenWork Electron browser automation with CDP. Use when driving a local Electron dev app, browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests.

SQL Injection — automated and manual exploitation of unsanitized SQL queries. Covers Union-based, Error-based, Blind (Boolean/Time-based), and Stacked queries. Includes sqlmap automation with WAF bypass tamper scripts.

Use when youtube-automation リポジトリ本体の新規リリースを作成したいとき。`/automation-release` 1 コマンドで状態判定し、prepare（リリース PR 作成）または publish（tag + GitHub Release）に自動分岐する。「リリースして」「リリース作って」「新しいバージョン作って」「v5.6.0 出して」「/automation-release」で発動。グローバル `/release` は Node.js 向けで本リポジトリでは使わない。

Automationen und Monitoring: Entwirft Monitore für Datenraum-Neuzugaenge, Q&A-Status, CP-Deadlines, Registerupdates, MAR-Signale und PMI-Aufgaben im Corporate/M&A-Kontext. Normen: MAR Art. 17, § 41 GWB (Vollzugsverbot), § 56 AWV.

Cross-browser and cross-device testing using BrowserStack or Sauce Labs

Browser automation tool. Used to capture project websites, DApp pages and other JS-rendered content, extract page text and interactive elements, and assist with research-oriented data collection.

Reviewer for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to review their work while removing complex Browser dependencies from tests.

ECC 的证据优先自动化清单和重叠审计工作流。当用户想要在修复任何内容之前知道哪些作业、钩子、连接器、MCP 服务器或包装器是活动的、损坏的、冗余的或缺失时使用。