openclaw-guide

OpenClaw 平台完整使用指南。涵盖 Gateway 配置、频道设置(Telegram/Discord/WhatsApp/微信等)、定时任务、会话管理、安全策略、沙盒配置、模型管理、Agent 管理、设备配对、心跳机制、CLI 命令等。当需要:(1) 配置或排查 OpenClaw (2) 添加频道/定时任务/设备 (3) 安全审计或沙盒配置 (4) 理解 OpenClaw 架构和工作原理 (5) 编写 Agent 技能或插件时使用。

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "openclaw-guide" with this command: npx skills add amazcuter/openclaw-doc

OpenClaw 使用指南

OpenClaw 是一个开源的 AI 个人助手框架,通过 Gateway 连接多种频道(Telegram、Discord、WhatsApp、微信等),配合模型提供商(Kimi、GLM、OpenRouter 等)提供智能助手能力。

快速命令

需求命令
查看状态openclaw status
切换模型/model kimi-coding/k2p5
压缩上下文/compact
健康检查openclaw doctor
安全审计openclaw security audit [--fix]

核心架构

  • Gateway: WebSocket 服务器,管理频道/节点/会话/hooks
  • Agent Loop: 用户消息 → 模型推理 → 工具调用 → 循环直到完成
  • Context Engine: 系统提示 + 工作区文件 + 对话历史 + 心跳
  • Compaction: 上下文接近窗口限制时自动压缩

文档导航

本 Skill 包含 212 篇 OpenClaw 官方文档完整内容,按目录组织:

核心概念 - references/concepts/

架构、Agent 循环、上下文引擎、模型故障转移、会话管理、记忆系统等 26 篇

Gateway - references/gateway/

配置、认证、安全、沙盒、心跳、远程访问、Tailscale、故障排除等 33 篇

CLI 命令 - references/cli/

所有子命令:config、gateway、models、sessions、devices、nodes、cron、security 等 46 篇

频道配置 - references/channels/

Telegram、Discord、WhatsApp、Signal、Slack、微信等各平台配置 29 篇

工具 - references/tools/

exec、browser、web、PDF、skills、subagents、thinking 等 25 篇

自动化 - references/automation/

cron 定时任务、webhook、hooks、投票、认证监控 11 篇

模型提供商 - references/providers/

Anthropic、GLM、Moonshot、OpenAI、OpenRouter、Ollama、Qwen 9 篇

入门指南 - references/start/

快速开始、安装、引导 5 篇

安全 - references/security/

威胁模型 1 篇

帮助 - references/help/

FAQ、调试、环境变量 4 篇

安装 - references/install/

Docker、Node.js、更新 4 篇

Web - references/web/

Dashboard、Control UI 3 篇

参考模板 - references/reference/

AGENTS.md、SOUL.md、BOOTSTRAP.md 等工作区模板 8 篇

其他

使用建议

遇到具体问题时,直接查阅对应目录下的文档。例如:

  • 配置 Telegram → references/channels/telegram.md
  • 设置定时任务 → references/automation/cron-jobs.md + references/cli/cron.md
  • 安全审计 → references/gateway/security/index.md + references/cli/security.md
  • 模型配置 → references/concepts/models.md + references/cli/models.md

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Spicy Ai Video

Turn a 60-second talking head clip into 1080p high-energy edited videos just by typing what you need. Whether it's turning bland footage into visually intens...

Registry SourceRecently Updated
Coding

Video Maker Fast

Get polished MP4 videos ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "trim...

Registry SourceRecently Updated
Coding

Generation Generator

generate text prompts or clips into AI generated videos with this skill. Works with MP4, MOV, PNG, JPG files up to 500MB. marketers, content creators, social...

Registry SourceRecently Updated
Coding

Editor On Android

Get edited MP4 clips ready to post, without touching a single slider. Upload your video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "trim th...

Registry SourceRecently Updated