
dingtalk-openclaw-connector
Connect OpenClaw AI agents to DingTalk with message handling, document operations, calendar, todos, and AI cards
- Installs
- 155
- 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 dingtalk-openclaw-connector- 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 dingtalk-openclaw-connector 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.
DingTalk OpenClaw Connector Skill
Skill by ara.so — Hermes Skills collection.
Official DingTalk channel plugin for OpenClaw, enabling AI agents to receive/send messages, manage documents, calendars, todos, and more within DingTalk enterprise workspace.
What It Does
This TypeScript connector bridges OpenClaw agents with DingTalk's ecosystem:
- Messaging: Receive/send private/group messages, @mentions, rich media (text/Markdown/images)
- Documents: Create, append, search, list DingTalk documents
- DING Notifications: Send priority alerts to users/groups
- Todos: Create personal todos, check status, set deadlines
- AI Tables: Create tables, read/write rows, query data
- Calendar: Manage calendars, events (CRUD + search), attendees, availability
- Journal: Submit daily/weekly reports, query history
- AI Cards: Streaming responses with typewriter effect, interactive buttons
- Multi-Agent Routing: Connect multiple bots to different OpenClaw agents
- Access Control: Flexible permission policies for private/group chats
Prerequisites
- OpenClaw ≥ 2026.4.9 (check:
openclaw -v, upgrade:npm install -g openclaw) - Node.js (for installation)
- DingTalk App (mobile, for QR authorization)
Installation
Quick Install with Auto-Authorization
npx -y @dingtalk-real-ai/dingtalk-connector install
Scan the QR code displayed in terminal with DingTalk mobile app. After seeing "Success! Bot configured.", restart gateway:
openclaw gateway restart
Manual Installation (if auto-auth fails)
npm install -g @dingtalk-real-ai/dingtalk-connector
Then follow manual setup guide to configure credentials.
Configuration
Plugin config is stored in OpenClaw's channel settings. Key environment variables:
# DingTalk bot credentials (obtained during authorization)
DINGTALK_CLIENT_ID=your_client_id
DINGTALK_CLIENT_SECRET=your_client_secret
DINGTALK_ROBOT_CODE=your_robot_code
# Optional: Multi-agent routing
DINGTALK_AGENT_MAPPING='{"bot_code_1":"agent_1","bot_code_2":"agent_2"}'
# Optional: Access control
DINGTALK_PRIVATE_CHAT_POLICY=whitelist # whitelist|blacklist|all
DINGTALK_GROUP_CHAT_POLICY=all # whitelist|blacklist|all
DINGTALK_WHITELIST=user_id_1,user_id_2
Access Control Policies
Configure who can interact with your bot:
// In OpenClaw channel config
{
"privateChatPolicy": "whitelist", // Only whitelisted users
"groupChatPolicy": "all", // All groups
"whitelist": ["user_123", "user_456"],
"blacklist": []
}
Options: all, whitelist, blacklist
Key Capabilities
1. Message Handling
The connector automatically receives and routes DingTalk messages to your OpenClaw agent:
// Agent receives message context
interface MessageContext {
conversationId: string;
senderId: string;
senderName: string;
content: {
text?: string;
images?: Array<{ downloadCode: string; url: string }>;
files?: Array<{ fileName: string; downloadCode: string }>;
};
isGroupChat: boolean;
atUsers?: string[];
}
2. Sending Messages
Text Message:
// Agent action
{
"action": "sendMessage",
"params": {
"conversationId": "cid_xxx",
"content": "Hello from OpenClaw!"
}
}
Markdown with @mention:
{
"action": "sendMessage",
"params": {
"conversationId": "cid_xxx",
"content": "## Report\n@user_123 please review",
"format": "markdown",
"atUsers": ["user_123"]
}
}
Image Message:
{
"action": "sendMessage",
"params": {
"conversationId": "cid_xxx",
"imageUrl": "https://example.com/image.png"
// Or local path: "imagePath": "/path/to/image.png"
}
}
3. AI Card Streaming
Show real-time thinking/generation progress:
// Enable in channel config
{
"enableAICard": true,
"streamingMode": "typewriter" // typewriter effect
}
The connector automatically wraps agent responses in interactive cards with states:
- 🤔 Thinking...
- ✍️ Generating...
- ✅ Complete
4. Document Operations
Create Document:
{
"action": "createDocument",
"params": {
"title": "Meeting Notes",
"content": "# Agenda\n- Item 1\n- Item 2",
"spaceId": "space_xxx" // optional
}
}
Append to Document:
{
"action": "appendDocument",
"params": {
"documentId": "doc_xxx",
"content": "\n## New Section\nAdditional notes..."
}
}
Search Documents:
{
"action": "searchDocuments",
"params": {
"keyword": "meeting",
"maxResults": 10
}
}
5. DING Notifications
Send high-priority alerts:
{
"action": "sendDing",
"params": {
"receiverUserIds": ["user_123", "user_456"],
"content": "Urgent: Server down!",
"remindType": "DING_SMS" // DING_NOTICE or DING_SMS
}
}
6. Todo Management
Create Todo:
{
"action": "createTodo",
"params": {
"subject": "Review PR #123",
"description": "Check code quality",
"dueTime": "2026-05-20T17:00:00Z",
"executorIds": ["user_123"]
}
}
Query Todos:
{
"action": "getTodos",
"params": {
"status": "PENDING", // PENDING|DONE
"startDate": "2026-05-01",
"endDate": "2026-05-31"
}
}
7. Calendar & Events
Create Calendar Event:
{
"action": "createCalendarEvent",
"params": {
"calendarId": "cal_xxx",
"summary": "Team Sync",
"startTime": "2026-05-20T14:00:00+08:00",
"endTime": "2026-05-20T15:00:00+08:00",
"location": "Conference Room A",
"attendees": [
{ "userId": "user_123" },
{ "userId": "user_456" }
]
}
}
Query Events:
{
"action": "searchCalendarEvents",
"params": {
"calendarId": "cal_xxx",
"startTime": "2026-05-20T00:00:00+08:00",
"endTime": "2026-05-21T00:00:00+08:00"
}
}
Check Availability:
{
"action": "checkAvailability",
"params": {
"userIds": ["user_123", "user_456"],
"startTime": "2026-05-20T14:00:00+08:00",
"endTime": "2026-05-20T15:00:00+08:00"
}
}
8. AI Tables
Create Table:
{
"action": "createAITable",
"params": {
"name": "Customer Database",
"fields": [
{ "name": "Name", "type": "TEXT" },
{ "name": "Email", "type": "TEXT" },
{ "name": "Status", "type": "SINGLE_SELECT", "options": ["Active", "Inactive"] }
]
}
}
Insert Row:
{
"action": "insertTableRow",
"params": {
"tableId": "tbl_xxx",
"fields": {
"Name": "John Doe",
"Email": "john@example.com",
"Status": "Active"
}
}
}
Query Rows:
{
"action": "queryTableRows",
"params": {
"tableId": "tbl_xxx",
"filter": {
"Status": "Active"
},
"maxResults": 50
}
}
9. Journal (Reports)
Submit Daily Report:
{
"action": "submitJournal",
"params": {
"type": "daily",
"date": "2026-05-20",
"content": "## Completed\n- Feature A\n- Bug fix B\n\n## Tomorrow\n- Feature C"
}
}
Query Reports:
{
"action": "getJournals",
"params": {
"type": "weekly",
"startDate": "2026-05-01",
"endDate": "2026-05-15"
}
}
Multi-Agent Routing
Connect multiple DingTalk bots to different OpenClaw agents for specialized tasks:
Configuration
# In .env or OpenClaw config
DINGTALK_AGENT_MAPPING='{
"robot_code_hr": "hr_agent",
"robot_code_it": "it_support_agent",
"robot_code_sales": "sales_agent"
}'
Agent Definitions
# openclaw.config.yaml
agents:
hr_agent:
name: HR Assistant
model: gpt-4
systemPrompt: You are an HR assistant handling employee queries
it_support_agent:
name: IT Support
model: gpt-4
systemPrompt: You provide IT technical support
sales_agent:
name: Sales Helper
model: gpt-4
systemPrompt: You assist with sales inquiries and CRM
Each bot routes to its designated agent automatically. See Multi-Agent Setup Guide.
Common Patterns
Pattern 1: Auto-Reply Bot
// Agent receives all group messages where bot is @mentioned
// Auto-respond with context-aware answers
async function handleMessage(context: MessageContext) {
const { content, isGroupChat, atUsers } = context;
if (isGroupChat && !atUsers?.includes(botUserId)) {
return; // Ignore if not @mentioned
}
const response = await generateResponse(content.text);
return {
action: "sendMessage",
params: {
conversationId: context.conversationId,
content: response
}
};
}
Pattern 2: Document Search Assistant
// Search docs and create summary
async function searchAndSummarize(query: string) {
// 1. Search documents
const docs = await executeAction({
action: "searchDocuments",
params: { keyword: query, maxResults: 5 }
});
// 2. Generate summary
const summary = await summarize(docs);
// 3. Create new doc with results
return executeAction({
action: "createDocument",
params: {
title: `Search Results: ${query}`,
content: summary
}
});
}
Pattern 3: Meeting Scheduler
// Find available slot and create event
async function scheduleMeeting(attendeeIds: string[], duration: number) {
const now = new Date();
const nextWeek = new Date(now.getTime() + 7 * 24 * 60 * 60 * 1000);
// 1. Check availability
const availability = await executeAction({
action: "checkAvailability",
params: {
userIds: attendeeIds,
startTime: now.toISOString(),
endTime: nextWeek.toISOString()
}
});
// 2. Find first free slot
const freeSlot = findFreeSlot(availability, duration);
// 3. Create event
return executeAction({
action: "createCalendarEvent",
params: {
summary: "Team Meeting",
startTime: freeSlot.start,
endTime: freeSlot.end,
attendees: attendeeIds.map(id => ({ userId: id }))
}
});
}
Pattern 4: Task Tracker Bot
// Create todo from message command
async function createTaskFromMessage(message: string, conversationId: string) {
// Parse: "todo: Review PR #123 by Friday"
const match = message.match(/todo:\s*(.+?)\s+by\s+(.+)/i);
if (!match) return;
const [, task, deadline] = match;
// Create todo
const todo = await executeAction({
action: "createTodo",
params: {
subject: task,
dueTime: parseDeadline(deadline)
}
});
// Confirm in chat
return executeAction({
action: "sendMessage",
params: {
conversationId,
content: `✅ Task created: ${task}\n📅 Due: ${deadline}`
}
});
}
Troubleshooting
Bot Not Responding
-
Check gateway status:
openclaw gateway status -
Restart gateway:
openclaw gateway restart -
Verify credentials:
# Check if config exists openclaw config list -
Check logs:
openclaw gateway logs
Authorization Failed
- Ensure you're using DingTalk mobile app (not desktop) to scan QR
- Check if QR code expired (timeout ~5 min), restart installation
- Verify network access to DingTalk API endpoints
Message Not Received
- Confirm bot is in the conversation (group chat: must add bot; private: user initiated)
- Check access control policies (whitelist/blacklist)
- Verify bot has required permissions in DingTalk admin console
Streaming AI Card Not Working
// Ensure enabled in config
{
"enableAICard": true,
"streamingMode": "typewriter"
}
- Feature requires OpenClaw ≥ 2026.4.9
- Check browser console for WebSocket errors
Multi-Agent Routing Issues
- Verify
DINGTALK_AGENT_MAPPINGJSON syntax - Ensure agent names match those in
openclaw.config.yaml - Check robot codes are correct (not client IDs)
Image Upload Fails
- Ensure image file exists and is readable
- Check file size (DingTalk limit: 20MB for images)
- Verify image format (JPEG, PNG, GIF supported)
- For URLs, ensure publicly accessible
Calendar Events Not Creating
- Verify user has calendar permissions in DingTalk
- Check time format (ISO 8601 with timezone)
- Ensure
calendarIdis valid (create calendar first if needed)
Common Error Codes
40014: Invalid access token → Re-authorize bot60020: Permission denied → Check DingTalk app permissions90002: Message frequency limit → Rate limiting, slow down71006: Robot not in conversation → Add bot to group/chat
Testing
Quick test after installation:
# Send test message to bot in DingTalk
# Expected: Bot responds with AI-generated reply in card format
Verify specific features:
// Test document creation
// In DingTalk: @bot create a document titled "Test"
// Test todo
// In DingTalk: @bot remind me to review code tomorrow
// Test search
// In DingTalk: @bot search for meeting notes from last week
Security Notes
- Model Risks: AI may hallucinate or execute unintended actions
- Authorization Scope: Bot operates with user permissions granted during setup
- Data Privacy: Follow company security policies if using corporate account
- Default Protections: Do NOT disable default security configs without understanding risks
- Recommended Use: Personal assistant, not production enterprise deployment
Additional Resources
- Manual Setup Guide
- DEAP Agent Integration (local device operations)
- Multi-Agent Routing Examples
- Troubleshooting Guide
- GitHub Issues
- CHANGELOG
FAQ
What does the dingtalk-openclaw-connector skill do?
Connect OpenClaw AI agents to DingTalk with message handling, document operations, calendar, todos, and AI cards
How do I install dingtalk-openclaw-connector?
Run npx skills add https://github.com/reason-machines/hermes-skills --skill dingtalk-openclaw-connector 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/dingtalk-openclaw-connector/ (personal) or .claude/skills/dingtalk-openclaw-connector/ (project).
Which AI agents can use dingtalk-openclaw-connector?
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 dingtalk-openclaw-connector 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 dingtalk-openclaw-connector?
It is published by reason-machines in reason-machines/hermes-skills. It has 155 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
Expert knowledge of the Hermes Agent ecosystem, skills, plugins, tools, integrations, and deployment patterns for building and extending AI agents
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
Native web workspace for Hermes Agent with chat, terminal, memory, skills, inspector, and multi-agent orchestration
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。