Openclaw Control Center

OpenClaw 可视化控制中心。当用户需要查看系统状态、打开控制台、监控 AI 运行指标、管理定时任务/会话/技能，或需要可视化运营面板时触发。触发词：打开控制中心 / 控制中心 / dashboard / 系统总览 / 系统状态。

This skill is coherent for a local control‑center/dashboard: it collects runtime info from OpenClaw and produces a static HTML you can open. Before installing or using '专业模式' (pro mode), be aware it will display sensitive items such as Session Keys, Tokens, Gateway endpoints and full cron/job payloads. Recommendations: 1) Keep READONLY_MODE or other safety defaults enabled on your Gateway if you will view the pro panel. 2) Do not place the skill into a shared/global skills folder if multiple users/agents can access the same workspace. 3) Inspect the generated control-center.html content before opening it in a browser (or open in a text editor) to confirm no secrets are being written you don't want exposed. 4) Avoid running the 'full deployment' steps (git clone / npm install / run) unless you trust the upstream repo and understand it will run a web server on a local port. If you need a safer setup, use the default 简洁模式 and avoid enabling/displaying the professional tables that include keys/tokens.

Type: OpenClaw Skill Name: openclaw-control-center Version: 1.0.0 The skill bundle functions as a system dashboard but requires high-privilege access to sensitive information, including session keys, API endpoints, and cron job payloads via tools like 'sessions_list' and 'gateway'. It instructs the AI agent to generate a local HTML file containing these secrets and then uses the 'exec' tool to execute a PowerShell command (Start-Process) to open it in a browser. While the intent appears to be functional visualization, the automated handling of session secrets combined with shell execution and the promotion of an external GitHub repository (TianyiDataScience/openclaw-control-center) for a 'full version' introduces significant security risks and potential for local data exposure.