一键导入
init-playwright
Initialize and verify AI Agent for web browser setup with Chrome for browser automation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Initialize and verify AI Agent for web browser setup with Chrome for browser automation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | init-playwright |
| description | Initialize and verify AI Agent for web browser setup with Chrome for browser automation. |
Verify that playwright-cli, Chrome, and the Playwright MCP Bridge extension are ready
before any browser automation is attempted.
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role, and Role-XYZ if you have more roles}, I will {action description}
keys-safe-guardplaywright-cliWhen this skill is used in a workflow agent node:
playwright-cli --version
If the command is not found:
pnpm install -g @playwright/cli@latest
playwright-cli --version
playwright-cli open --extension --headed
Treat this as an initialization flow, not a blocking foreground command:
playwright-cli open --extension --headed.Interpret the result as follows:
Browser \default` opened with pid ...`, the browser bridge is ready.Extension connection timeout. Make sure the "Playwright MCP Bridge" extension is installed., go to Step 3 and instruct the user to install the Chrome extension.PLAYWRIGHT_MCP_EXTENSION_TOKEN value.If you get an error that Chrome is not installed
pnpm exec playwright install chrome # install the official branded Google Chrome browser
Once Chrome is installed, go to Step 2 and test the browser + extension bridge.
If the Chrome extension is not installed:
Ask the user to open Chrome and install the Playwright MCP Bridge extension using the URL below:
https://chromewebstore.google.com/detail/playwright-mcp-bridge/mmlmfjhmonkocbjadbfplnigmagldckm
Ask the user to confirm once the installation is complete, then go to Step 2 and test the browser + extension bridge.
If the extension is ready and waiting for authentication, give the user two options:
The token format shown on the Chrome extension screen is:
PLAYWRIGHT_MCP_EXTENSION_TOKEN=xxxxxxxx_xxxxxxx_xxx_xxxxxxxxxxxxxxxxxxxxxx
If the user provides a token, kill the background playwright-cli open --extension --headed process, then verify it without saving anything:
PLAYWRIGHT_MCP_EXTENSION_TOKEN=token-string playwright-cli open --extension --headed
The verification is successful only if the command responds immediately with text like:
Browser `default` opened with pid 44554.
If verification succeeds, use the keys-safe-guard skill to save PLAYWRIGHT_MCP_EXTENSION_TOKEN into config/.env.
Otherwise, the command will return Extension connection timeout. Make sure the "Playwright MCP Bridge" extension is installed., but the user sees Invalid token provided in the web browser.
In this case, ask the user to check the web browser if it shows the message Invalid token provided.
If it is showing Invalid token provided, issue another command without the token:
playwright-cli open --extension --headed
Then tell the user the token is invalid and ask for a new token.
If the user does not want to paste a token, tell them they can manually approve the extension each time browser automation starts.
Or the user can set the PLAYWRIGHT_MCP_EXTENSION_TOKEN token in config/.env manually, then restart the service with the shell command core/bin/tool-cli engine-reload, and refresh the webui to restart the task afterward.
Until the command below gets the correct response, then go to Step 4.
PLAYWRIGHT_MCP_EXTENSION_TOKEN=token-string playwright-cli open --extension --headed
playwright-cli list
The output should be:
### Browsers
- default:
- status: open
- browser-type: chrome
- user-data-dir: <in-memory>
- headed: true
Output result as plain text, say "Default Google Chrome has been opened and is ready to use. Open any web URL using: playwright-cli goto URL by agent skill playwright-cli." If the user asked to save it to a file, write it there.
Plain text result shown to user (example):
Playwright CLI: ready
Chrome: Opened and ready to use
MCP Bridge extension: connected
Token setup: verified and saved with keys-safe-guard, or manual approval required
Open any web URL using: `playwright-cli goto URL` by agent skill `playwright-cli`
If the user requested file output, write the same content to the specified path.
npm install -g @playwright/cli@latest insteadReverse-engineer an existing software project so the user can understand the code logic, architecture, workflows, design decisions, and potential issues. Use this when the user provides a GitHub repo, local codebase, zip file, or existing project and wants architecture understanding, Mermaid diagrams, remake guidance in another language, or expert design/performance evaluation.
Perform deep research from a research requirement or instruction file and produce research outputs in the same folder, including Markdown plus an index.html visual report with Mermaid diagrams when useful.
Open and operate the local Skill Pilot WebUI through the browser for demos, walkthroughs, settings changes, task execution, and terminal-based education flows. Use when the user wants the agent to drive Skill Pilot as a human would in the browser, open a specific WebUI feature, or jump directly into shell or agent terminal views.
Use this skill when acting as a Black-Box Code Agent Supervisor. The supervisor uses coding agent CLIs such as Claude Code, Codex, OpenCode, Gemini CLI, or other AI coding agents through tmux terminal windows to finish a coding task or project. The supervisor works like a real developer using AI agents: giving instructions, checking the running result, using browser/curl/logs, finding issues, and sending feedback back to the coding agent. The supervisor does not directly inspect source code, write code, or write code-level tests.
Manage the full lifecycle of a Vibe Coding project — create, refine, brainstorm, initialize, plan, implement, review, test, deploy, update, and fix issues. Use when the user wants to start a new project from a prompt, evolve its requirements, plan or write code, validate or deploy it, or apply updates and bug fixes against an existing project.
Create interactive courses and assignments for students in the project's markdown format. Use when asked to create a new course, educational module, or assignment.