Menü
Install and configure Playwright MCP for browser automation
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Authoritative, version-pinned reference for every Claude Code CLI flag, classified by whether it works in an INTERACTIVE session (default TUI), a HEADLESS session (-p/--print), or BOTH — plus the canonical launch recipes for each mode. Use when any session needs to launch or script `claude` and must know which switch is valid in which mode, build a headless/streaming invocation, set up remote-control or an always-on session, pass model/effort/permissions/MCP/plugin/settings flags, or answer "does flag X work with -p / in interactive". Trigger: "claude flags", "claude cli switches", "which flags work headless vs interactive", "-p flags", "stream-json flags", "how do I launch claude with X", "/claude-cli-flags".
Authoritative, version-pinned reference for every built-in Claude Code slash (/) command — what each does, its aliases, and which are bundled Skills/Workflows vs fixed built-ins — plus how custom slash commands work (the commands-merged-into-skills model, file locations, frontmatter, arguments, !bash, @file). Includes the full /loop vs /schedule breakdown. Use when any session needs to know what a slash command does, find the right command for a task (clear context, switch model, review code, schedule work, background a task), or author a custom /command. Trigger: "claude slash commands", "what does /X do", "list the slash commands", "built-in commands", "custom slash command", "/loop vs /schedule", "how do I make a /command", "/claude-slash-commands". Sibling of claude-cli-flags (launch flags).
Initialise a workspace, register projects under it, or sync upstream changes. Single entry point for workspace lifecycle.
Enforce coordinated integration testing — identify tool dependencies, check running systems, test all 4 levels (unit/component/integration/system), never disrupt workflows
Autonomous task loop — runs a task repeatedly until completion criteria are met. No babysitting required.
Dual-model review — runs the same question past a second, independent reasoner (a separate model/CLI, e.g. Codex) and synthesizes the disagreements with the primary Claude take. Use before an irreversible call — architecture, security, strategy, high-blast-radius code. Trigger phrases "second opinion", "/second-opinion", "review this", "get another perspective", "sanity check this plan".
| name | setup-playwright-mcp |
| description | Install and configure Playwright MCP for browser automation |
| user_invocable | true |
You are helping the user add the Playwright MCP server, which gives Claude Code the ability to interact with web browsers (navigate, click, fill forms, take screenshots, etc.).
Verify the following are available:
node --versionnpx --versionIf either is missing, search the web for current installation instructions for the user's detected OS/platform and help them install it.
Run a quick smoke test to confirm the package can be fetched and started:
npx @playwright/mcp --help (or start it briefly with a timeout).mcp.json EntryMerge the following entry into .mcp.json in the project root:
{
"playwright": {
"command": "npx",
"args": ["@playwright/mcp"]
}
}
Rules:
.mcp.json already exists with other servers (e.g., cognee), merge — do not overwrite existing entries.mcp.json doesn't exist, create it with just this entry.mcp.json in .gitignoreCheck .gitignore for .mcp.json. If not already listed, add it. The file may contain secrets from other server configs and is machine-specific.
Run /mcp-doctor to confirm the playwright server is reachable and reports its tools.
Summarize what was configured:
Playwright MCP Setup Complete
==============================
Node.js: (detected version)
npx: available
.mcp.json: playwright entry added
.gitignore: .mcp.json entry present
Health check: passed / failed
⚠ Restart Claude Code for the new MCP server to load.
Available capabilities:
- Browser navigation and interaction
- Form filling and clicking
- Screenshot capture
- JavaScript execution in browser context
Next steps:
- Restart Claude Code to activate the server
- Ask Claude Code to open a URL or interact with a web page