Openclaw Docs

OpenClaw 官方文档知识库。当用户询问 OpenClaw 相关问题时自动触发，包括：安装配置、CLI 命令、渠道设置（飞书/钉钉/WhatsApp 等）、定时任务（cron）、技能开发、故障排查。提供命令示例和配置模板。

This skill is instruction-only and appears coherent with its documentation purpose. Before installing or following commands: verify the official OpenClaw documentation links/domains (docs.openclaw.ai) are legitimate, avoid pasting real API keys or secrets into chat, and if you plan to run example install commands (e.g., npm install -g openclaw@latest) confirm the npm package source and maintainer (there's no homepage listed in the package.json).

Type: OpenClaw Skill Name: openclaw-docs-cn Version: 1.1.0 The skill provides instructions for the AI agent to output system-modifying commands such as `npm install -g openclaw@latest`, `openclaw onboard --install-daemon`, and instructions to edit configuration files like `~/.openclaw/openclaw.json` (found in SKILL.md). While these commands are legitimate for the stated purpose of OpenClaw documentation and management, and the skill explicitly instructs the agent *not* to provide real secrets or sensitive information, the capability for an AI agent to provide such system-altering commands constitutes a 'risky capability' that could lead to unintended consequences or be exploited if the agent's execution environment lacks proper sandboxing or user confirmation mechanisms. There is no evidence of malicious intent, but the inherent risk elevates it beyond benign.