Openclaw logo

Openclaw

Community
znlgis
openclaw

Use when setting up a multi-channel personal AI assistant gateway bridging chat platforms (Telegram, Discord, WhatsApp, WeChat) with LLM backends. OpenClaw: multi-channel AI assistant gateway for unified personal AI access.

Overview

Publisherznlgis
Repositoryopengis-skills
Skill nameopenclaw
Stars
76
Forks
12
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by znlgis on GitHub. Read the source before you install it.

Installation

Install the Openclaw AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/znlgis/opengis-skills/tree/main/ai/openclaw
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/znlgis/opengis-skills.git /tmp/opengis-skills
mkdir -p .claude/skills
cp -r /tmp/opengis-skills/ai/openclaw .claude/skills/openclaw
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Openclaw in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Openclaw on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Openclaw is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

项目地址: https://github.com/openclaw/openclaw

官网 / 文档: https://openclaw.ai | https://docs.openclaw.ai

许可证: MIT | 语言: TypeScript

最新版本: v2026.10.8(日历版本号,截至 2026-10,见 Releases)

运行时: Node 24.22.1+ 或 26.12.1+(推荐 Node 26) 发布频道: latest / beta / dev(参见 GitHub Releases)

注意: OpenClaw 的助手可以执行命令、读写文件、控制设备并接入你的私人聊天账号。对外暴露前务必阅读官方 Security、Exposure runbook 与 Sandboxing,并配置沙箱与访问控制。默认情况下主会话的工具直接在宿主机上执行。

配对机制: 能收私信(DM)的通道默认对陌生发送者启用配对,用 openclaw pairing approve <channel> <code> 批准。

概述

OpenClaw 是「本地优先、单一信任边界、面向个人助手场景的多通道 AI Gateway」。聊天平台只是入口,真正的核心是常驻的 Gateway(控制平面),负责会话、通道、模型、工具、节点、技能、插件、配置与安全策略。

  • 本地优先 Gateway:单一控制平面,统一管理 sessions / channels / tools / events。
  • 多通道接入:WhatsApp、Telegram、Slack、Discord、Google Chat、Signal、iMessage、IRC、Microsoft Teams、Matrix、飞书(Feishu)、LINE、Mattermost、Nextcloud Talk、Nostr、Synology Chat、Tlon、Twitch、Zalo、微信(WeChat)、QQ、WebChat 等。
  • 多智能体路由:把不同通道/账号/对端路由到隔离的 agent(独立 workspace 与会话)。
  • 工具与沙箱:每类工具可 allow/ask/deny;典型默认放行 bash/process/read/write/edit/sessions_*,默认拒绝 browser/canvas/nodes/cron/discord/gateway。
  • 节点(Nodes):手机/桌面作为节点通过 Gateway WebSocket 配对,暴露设备能力(语音、屏幕、Canvas)。
  • Control UI / Canvas / 语音:可在 macOS/iOS/Android 上听说,并渲染可交互的实时 Canvas。

安装与启动

推荐用引导式 onboard(支持 macOS / Linux / Windows):

bash
# npm 12 或 11.16+ 用带 --allow-scripts 的写法(安装脚本需要执行)
npm install -g openclaw@latest --allow-scripts=openclaw
# npm 11.15 及更早:去掉 --allow-scripts=openclaw
# 或 pnpm add -g openclaw@latest

# 引导设置 Gateway、workspace、通道、技能,并安装常驻守护进程(launchd/systemd 用户服务)
openclaw onboard --install-daemon

# Gateway 管理
openclaw gateway status
openclaw gateway stop
openclaw gateway --port 18789 --verbose   # 默认端口 18789
openclaw dashboard                        # 打开 Control UI,发一条消息确认助手可用

验证安装:

bash
node -v                # 需要 24.22.1+ 或 26.12.1+
openclaw --version
openclaw gateway status

最小配置 ~/.openclaw/openclaw.json(仅设置模型与默认值,JSON5 语法):

json5
{
  agent: {
    model: "<provider>/<model-id>",
  },
}

完整配置项见官方 Configuration。也支持 Docker 安装 与 Nix。

发布通道:latest(稳定,tag vYYYY.M.D)、beta(预发布)、dev(main 头部)。


典型工作流

text
1. openclaw onboard --install-daemon     # 初始化 Gateway + workspace + 通道
2. 在 onboard 中接入至少一个聊天通道(如 Telegram)与一个模型 Provider
3. 在手机用 Telegram/WhatsApp 直接与助手对话;桌面用 Control UI 观察与控制
4. 按需开启工具(bash/process/...)、节点(设备能力)、cron(定时任务)
5. 暴露到公网前:配置沙箱、访问控制,按 Exposure runbook 加固

多智能体:在 openclaw.json 中把不同通道/账号路由到不同 agent,实现「工作助手」「家庭助手」隔离运行(各自 workspace 与会话历史)。


核心概念:信任边界与沙箱

  • 默认最小权限:保持危险工具(browser/canvas/nodes/cron/gateway)默认 deny,仅按需开启。
  • 远程暴露分层加固:优先用 Tailscale 等私有网络,而非裸公网;务必读 Remote access 与 Exposure runbook。
  • 隔离运行:用专用账户/容器/虚拟机运行 Gateway,限制其可访问的文件与命令。
  • 审计:通过 events 与日志观察助手实际执行的工具调用。

本地开发(源码)

仓库是 pnpm workspace:

bash
pnpm install
pnpm openclaw setup          # 写入本地 config/workspace(首次或重置后)
pnpm ui:build                # 构建 Control UI
pnpm gateway:watch           # 开发期按需重建运行时
# UI 迭代:pnpm ui:dev;生产构建:pnpm build 产出 dist/

pnpm openclaw ... 经 tsx 直接运行 TypeScript;pnpm gateway:watch 不会重建 dist/control-ui,改动 ui/ 后需重跑 pnpm ui:build。


常见问题(FAQ)

问题解决
OpenClaw 是桌面 RPA / Computer Use 吗?不是。它是多通道个人助手 Gateway,核心是控制平面,聊天平台是入口
Gateway 没保持运行用 openclaw onboard --install-daemon 安装守护进程;openclaw gateway status 检查
通道连不上在 onboard 中重新配置该通道凭证;不同平台的默认行为见官方 Channels 文档
助手执行了危险命令收紧沙箱,把 bash/process 等设为 ask/deny,限定可用工具
想远程访问优先 Tailscale 等私网;公网暴露前按 Security + Exposure runbook 加固
端口冲突openclaw gateway --port <port>(默认 18789)
npm install -g openclaw 装完命令没了或没跑起来npm 12 / 11.16+ 必须带 --allow-scripts=openclaw 才会执行安装脚本;早期 npm 则不能带该参数
启动报 Node 版本不符OpenClaw 要求 Node 24.22.1+ 或 26.12.1+;node -v 确认后升级
多账号互相串话用多智能体路由,把通道/账号映射到隔离 agent(独立 workspace)

AI 使用建议

  • 用户提到「个人 AI 助手网关」「把 Telegram/WhatsApp/微信接到一个 AI」「self-hosted assistant gateway」「OpenClaw」时加载本技能。
  • 先澄清:接哪些通道、用什么模型、是否需要节点/语音/Canvas、是否对外暴露。
  • 生成命令以 openclaw onboard 为起点,配置写 ~/.openclaw/openclaw.json;强调最小权限沙箱与暴露前加固。
  • 不要把 OpenClaw 误描述为桌面操作/Computer Use 工具——它是多通道助手 Gateway。

相关技能


参考资源

Frequently asked questions

What does the Openclaw AI skill do?

Use when setting up a multi-channel personal AI assistant gateway bridging chat platforms (Telegram, Discord, WhatsApp, WeChat) with LLM backends. OpenClaw: multi-channel AI assistant gateway for unified personal AI access.

Why use Openclaw on TypingMind?

Because you install it once and use it with any model. Openclaw is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Openclaw in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/znlgis/opengis-skills/tree/main/ai/openclaw. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Openclaw?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Openclaw?

As many as you like. As long as a model supports skills, you can use Openclaw with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Openclaw AI skill free?

Yes. It is published on GitHub by znlgis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇