
openclaw-china-integration
Expert in integrating OpenClaw AI with Chinese IM platforms (DingTalk, Feishu, QQ, WeChat Work, WeChat Official Account)
- Installs
- 171
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-china-integration- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads openclaw-china-integration automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
OpenClaw China Integration Skill
Skill by ara.so — Hermes Skills collection.
OpenClaw China is a comprehensive plugin collection that extends OpenClaw to support major Chinese instant messaging platforms including DingTalk (钉钉), Feishu (飞书), QQ, WeChat Work (企业微信), WeChat Official Account (微信公众号), and WeChat Customer Service (微信客服).
What OpenClaw China Does
- Multi-Platform Support: Connects OpenClaw AI agents to 6+ Chinese IM platforms
- Unified Interface: Provides consistent message handling across different platforms
- Rich Features: Supports text, Markdown, images, files, voice messages, and streaming responses
- Enterprise Ready: Handles both internal (WeChat Work) and external (WeChat Customer Service) users
- Low Configuration: Simplified setup process with guided installation
Installation
Quick Setup (Recommended)
npx @openclaw-china/setup
This interactive installer will:
- Check your OpenClaw installation
- Guide you through platform selection
- Generate configuration files
- Install required dependencies
Manual Installation
# Install OpenClaw China packages
npm install @openclaw-china/dingtalk @openclaw-china/qqbot @openclaw-china/wecom @openclaw-china/wecom-app @openclaw-china/wecom-kf @openclaw-china/wechat-mp
# Or install specific channels
npm install @openclaw-china/dingtalk # DingTalk only
npm install @openclaw-china/qqbot # QQ Bot only
npm install @openclaw-china/wecom # WeChat Work Robot only
Platform Selection Guide
| Platform | Complexity | Public IP Required | Use Case |
|---|---|---|---|
| DingTalk | Simple | No | Enterprise internal |
| QQ Bot | Simple | No | Public bot service |
| WeChat Work Robot | Simple | No | Enterprise internal (recommended) |
| WeChat Work App | Medium | Yes | Connect to personal WeChat |
| WeChat Customer Service | Medium | Yes | External customer support |
| WeChat Official Account | Medium | Yes | Public followers |
Configuration
DingTalk Configuration
// config/channels.dingtalk.ts
export default {
channels: {
dingtalk: {
enabled: true,
clientId: process.env.DINGTALK_CLIENT_ID,
clientSecret: process.env.DINGTALK_CLIENT_SECRET,
// Optional: Enable multiple accounts
accounts: [
{
clientId: process.env.DINGTALK_CLIENT_ID_1,
clientSecret: process.env.DINGTALK_CLIENT_SECRET_1
}
]
}
}
}
Environment variables:
DINGTALK_CLIENT_ID=your_client_id
DINGTALK_CLIENT_SECRET=your_client_secret
QQ Bot Configuration
// config/channels.qqbot-china.ts
export default {
channels: {
'qqbot-china': {
enabled: true,
appId: process.env.QQ_APP_ID,
token: process.env.QQ_BOT_TOKEN,
// Enable streaming for C2C (private chat)
streaming: true,
// Optional: Enable multiple bots
accounts: [
{
appId: process.env.QQ_APP_ID_1,
token: process.env.QQ_BOT_TOKEN_1,
secret: process.env.QQ_BOT_SECRET_1
}
]
}
}
}
WeChat Work Robot (Long Connection)
// config/channels.wecom.ts
export default {
channels: {
wecom: {
enabled: true,
corpId: process.env.WECOM_CORP_ID,
corpSecret: process.env.WECOM_CORP_SECRET,
// Connection mode: 'ws' (WebSocket) or 'webhook'
mode: 'ws',
// Optional: Robot token for webhook mode
token: process.env.WECOM_ROBOT_TOKEN,
encodingAESKey: process.env.WECOM_ENCODING_AES_KEY
}
}
}
WeChat Work Self-Built App (Can Connect to Personal WeChat)
// config/channels.wecom-app.ts
export default {
channels: {
'wecom-app': {
enabled: true,
corpId: process.env.WECOM_APP_CORP_ID,
agentId: process.env.WECOM_APP_AGENT_ID,
secret: process.env.WECOM_APP_SECRET,
token: process.env.WECOM_APP_TOKEN,
encodingAESKey: process.env.WECOM_APP_ENCODING_AES_KEY,
// Public URL for callbacks
callbackUrl: process.env.WECOM_APP_CALLBACK_URL
}
}
}
WeChat Customer Service (External Users)
// config/channels.wecom-kf.ts
export default {
channels: {
'wecom-kf': {
enabled: true,
corpId: process.env.WECOM_KF_CORP_ID,
secret: process.env.WECOM_KF_SECRET,
token: process.env.WECOM_KF_TOKEN,
encodingAESKey: process.env.WECOM_KF_ENCODING_AES_KEY,
// Welcome message when user enters session
welcomeMessage: '您好!我是AI助手,有什么可以帮您?'
}
}
}
WeChat Official Account
// config/channels.wechat-mp.ts
export default {
channels: {
'wechat-mp': {
enabled: true,
appId: process.env.WECHAT_MP_APP_ID,
appSecret: process.env.WECHAT_MP_APP_SECRET,
token: process.env.WECHAT_MP_TOKEN,
encodingAESKey: process.env.WECHAT_MP_ENCODING_AES_KEY,
// Render Markdown to plain text for WeChat compatibility
renderMarkdown: true,
// Active delivery mode: 'split' (multiple messages) or 'merged' (single message)
activeDeliveryMode: 'split',
// ASR (Automatic Speech Recognition) for voice messages
asrConfig: {
enabled: true,
secretId: process.env.TENCENT_CLOUD_SECRET_ID,
secretKey: process.env.TENCENT_CLOUD_SECRET_KEY,
engineType: '16k_zh' // 16kHz Chinese
}
}
}
}
Real Code Examples
Handling Incoming Messages
// Custom message handler for DingTalk
import { DingTalkChannel } from '@openclaw-china/dingtalk';
const channel = new DingTalkChannel({
clientId: process.env.DINGTALK_CLIENT_ID,
clientSecret: process.env.DINGTALK_CLIENT_SECRET
});
// Listen for messages
channel.on('message', async (message) => {
console.log('Received:', message.content);
// Process with OpenClaw
const response = await openclawAgent.chat(message.content);
// Send response
await channel.sendMessage({
conversationId: message.conversationId,
content: response.text,
messageType: 'markdown' // or 'text'
});
});
Sending Proactive Messages (Scheduled Tasks)
// Send scheduled message via QQ Bot
import { QQBotChannel } from '@openclaw-china/qqbot';
const qqBot = new QQBotChannel({
appId: process.env.QQ_APP_ID,
token: process.env.QQ_BOT_TOKEN
});
async function sendDailyReport() {
const report = await generateReport();
await qqBot.sendMessage({
userId: 'user_openid',
content: report,
messageType: 'markdown'
});
}
// Schedule daily at 9 AM
cron.schedule('0 9 * * *', sendDailyReport);
Handling File Uploads
// Process file from WeChat Work
import { WeComAppChannel } from '@openclaw-china/wecom-app';
const wecomApp = new WeComAppChannel({
corpId: process.env.WECOM_APP_CORP_ID,
agentId: process.env.WECOM_APP_AGENT_ID,
secret: process.env.WECOM_APP_SECRET
});
wecomApp.on('file', async (fileMessage) => {
// Download file
const fileBuffer = await wecomApp.downloadMedia(fileMessage.mediaId);
// Process with OpenClaw
const analysis = await openclawAgent.analyzeFile(fileBuffer);
// Send response
await wecomApp.sendMessage({
userId: fileMessage.fromUserId,
content: `文件分析结果:\n${analysis}`
});
});
Streaming Response (QQ Bot C2C)
// Enable streaming for real-time chat experience
import { QQBotChannel } from '@openclaw-china/qqbot';
const qqBot = new QQBotChannel({
appId: process.env.QQ_APP_ID,
token: process.env.QQ_BOT_TOKEN,
streaming: true // Enable streaming for private chat
});
qqBot.on('message', async (message) => {
// Streaming only works for C2C (private chat)
if (message.messageType === 'C2C') {
const stream = await openclawAgent.chatStream(message.content);
for await (const chunk of stream) {
await qqBot.updateStreamMessage({
messageId: message.id,
content: chunk.text
});
}
} else {
// Group chat falls back to regular message
const response = await openclawAgent.chat(message.content);
await qqBot.sendMessage({
groupId: message.groupId,
content: response.text
});
}
});
Voice Message with ASR (WeChat Official Account)
// Automatic voice-to-text conversion
import { WeChatMPChannel } from '@openclaw-china/wechat-mp';
const wechatMP = new WeChatMPChannel({
appId: process.env.WECHAT_MP_APP_ID,
appSecret: process.env.WECHAT_MP_APP_SECRET,
asrConfig: {
enabled: true,
secretId: process.env.TENCENT_CLOUD_SECRET_ID,
secretKey: process.env.TENCENT_CLOUD_SECRET_KEY,
engineType: '16k_zh'
}
});
wechatMP.on('voice', async (voiceMessage) => {
// ASR automatically converts voice to text
const text = voiceMessage.recognizedText;
console.log('Voice recognized:', text);
// Process with OpenClaw
const response = await openclawAgent.chat(text);
await wechatMP.sendMessage({
userId: voiceMessage.fromUserId,
content: response.text
});
});
Common Patterns
Multi-Account Setup
// config/channels.dingtalk.ts
export default {
channels: {
dingtalk: {
enabled: true,
accounts: [
{
name: 'team-a',
clientId: process.env.DINGTALK_TEAM_A_CLIENT_ID,
clientSecret: process.env.DINGTALK_TEAM_A_CLIENT_SECRET
},
{
name: 'team-b',
clientId: process.env.DINGTALK_TEAM_B_CLIENT_ID,
clientSecret: process.env.DINGTALK_TEAM_B_CLIENT_SECRET
}
]
}
}
}
Group Chat Management
// Handle @mentions in WeChat Work group
import { WeComChannel } from '@openclaw-china/wecom';
const wecom = new WeComChannel({
corpId: process.env.WECOM_CORP_ID,
corpSecret: process.env.WECOM_CORP_SECRET,
mode: 'ws'
});
wecom.on('message', async (message) => {
// Check if bot is mentioned in group
if (message.isGroupChat && message.isMentioned) {
const cleanContent = message.content.replace(/@\w+/g, '').trim();
const response = await openclawAgent.chat(cleanContent, {
context: {
groupId: message.groupId,
userId: message.fromUserId
}
});
await wecom.sendMessage({
groupId: message.groupId,
content: response.text,
mentionedUsers: [message.fromUserId] // @user in response
});
}
});
Message Formatting
// Convert Markdown to platform-specific format
function formatMessage(text: string, platform: string): string {
switch (platform) {
case 'dingtalk':
case 'wecom':
case 'qqbot':
// These support Markdown
return text;
case 'wechat-mp':
// Convert Markdown to plain text
return text
.replace(/\*\*(.+?)\*\*/g, '$1') // Bold
.replace(/\*(.+?)\*/g, '$1') // Italic
.replace(/`(.+?)`/g, '$1') // Code
.replace(/^#+\s+(.+)$/gm, '$1'); // Headers
default:
return text;
}
}
Troubleshooting
Connection Issues
Problem: WebSocket connection fails for WeChat Work Robot
// Solution: Check network and enable debug logging
const wecom = new WeComChannel({
corpId: process.env.WECOM_CORP_ID,
corpSecret: process.env.WECOM_CORP_SECRET,
mode: 'ws',
debug: true // Enable debug logs
});
wecom.on('error', (error) => {
console.error('WeChat Work error:', error);
// Implement retry logic
});
wecom.on('disconnect', () => {
console.log('Disconnected, reconnecting...');
setTimeout(() => wecom.connect(), 5000);
});
Problem: Callback URL not receiving messages
# Verify your public URL is accessible
curl https://your-domain.com/webhook/wecom-app
# Check nginx/reverse proxy configuration
# Ensure SSL certificate is valid
# Verify firewall allows incoming connections
Message Delivery Issues
Problem: Messages not sending on WeChat Official Account
// Check 48-hour interaction window
import { WeChatMPChannel } from '@openclaw-china/wechat-mp';
const wechatMP = new WeChatMPChannel({
appId: process.env.WECHAT_MP_APP_ID,
appSecret: process.env.WECHAT_MP_APP_SECRET
});
try {
await wechatMP.sendMessage({
userId: 'user_openid',
content: 'Hello'
});
} catch (error) {
if (error.code === 45015) {
console.error('Outside 48-hour window, use template message instead');
await wechatMP.sendTemplateMessage({
userId: 'user_openid',
templateId: process.env.TEMPLATE_ID,
data: { message: 'Hello' }
});
}
}
Problem: Messages truncated or not displaying
// Enable automatic message splitting for long content
const wechatMP = new WeChatMPChannel({
appId: process.env.WECHAT_MP_APP_ID,
appSecret: process.env.WECHAT_MP_APP_SECRET,
activeDeliveryMode: 'split', // Split long messages automatically
renderMarkdown: true // Convert Markdown to plain text
});
Platform-Specific Issues
QQ Bot: Streaming not working in groups
// Streaming only supports C2C (private chat)
const qqBot = new QQBotChannel({
appId: process.env.QQ_APP_ID,
token: process.env.QQ_BOT_TOKEN,
streaming: true // Only applies to private chat
});
// For groups, use regular messages
qqBot.on('message', async (message) => {
if (message.messageType === 'GROUP') {
// No streaming in groups, send complete message
const response = await openclawAgent.chat(message.content);
await qqBot.sendMessage({
groupId: message.groupId,
content: response.text
});
}
});
DingTalk: Rate limiting
// Implement rate limiting
import { RateLimiter } from 'limiter';
const limiter = new RateLimiter({
tokensPerInterval: 20,
interval: 'minute'
});
async function sendDingTalkMessage(message) {
await limiter.removeTokens(1);
return dingtalk.sendMessage(message);
}
Debug Mode
// Enable verbose logging for troubleshooting
export default {
channels: {
'qqbot-china': {
enabled: true,
debug: true, // Enable debug logs
appId: process.env.QQ_APP_ID,
token: process.env.QQ_BOT_TOKEN
}
},
logging: {
level: 'debug', // Set global log level
channels: ['qqbot-china'] // Log specific channels
}
}
Feature Support Matrix
| Feature | DingTalk | QQ Bot | WeChat Work Robot | WeChat Work App | WeChat Customer Service | WeChat Official Account |
|---|---|---|---|---|---|---|
| Text Messages | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Markdown | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ (converted) |
| Streaming | ✅ | ✅ (C2C only) | ✅ | ❌ | ❌ | ❌ |
| Images/Files | ✅ | ✅ | ✅ | ✅ | 🚧 | ✅ (images only) |
| Voice | ✅ | ✅ | ✅ | ✅ | 🚧 | ✅ (with ASR) |
| Group Chat | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
| Multi-Account | ✅ | ✅ | ✅ | ✅ | 🚧 | 🚧 |
| Proactive Send | ✅ | ✅ | ✅ | ✅ | 🚧 | 🚧 |
Legend: ✅ Supported | ❌ Not Supported | 🚧 In Development
FAQ
What does the openclaw-china-integration skill do?
Expert in integrating OpenClaw AI with Chinese IM platforms (DingTalk, Feishu, QQ, WeChat Work, WeChat Official Account)
How do I install openclaw-china-integration?
Run npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-china-integration in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/openclaw-china-integration/ (personal) or .claude/skills/openclaw-china-integration/ (project).
Which AI agents can use openclaw-china-integration?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is openclaw-china-integration safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains openclaw-china-integration?
It is published by reason-machines in reason-machines/hermes-skills. It has 171 recorded installs.
More from reason-machines/hermes-skills
hermes-agent-self-evolution
reason-machines/hermes-skills
Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code
hermes-webui-agent
reason-machines/hermes-skills
Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.
awesome-hermes-agent-ecosystem
reason-machines/hermes-skills
Open the skill to read its SKILL.md instructions.
hermes-agent-framework
reason-machines/hermes-skills
Hermes Agent framework by Nous Research - self-improving AI agent with built-in learning loop, three-layer memory, and automatic skill evolution
hermes-workspace-ai-agent-ui
reason-machines/hermes-skills
Open the skill to read its SKILL.md instructions.
hermes-web-ui-dashboard
reason-machines/hermes-skills
Web dashboard for managing Hermes Agent multi-platform AI chat sessions, analytics, scheduled jobs, and platform channels
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。