Integrate Openclaw with WeCom using official Tencent plugins and WebSocket long-polling for secure, firewall-friendly AI chat capabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wecom-setup
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install wecom-setup using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is WeCom Channel Integration?
The WeCom Channel Integration is a professional-grade skill designed to bridge the gap between Openclaw and the enterprise communication platform WeCom (Work WeChat). By leveraging the official Tencent WebSocket plugin, this skill allows developers to deploy AI agents directly into corporate environments without the need for complex domain configurations or public IP whitelisting. It is a core component for teams building internal tools within the Openclaw Skills ecosystem.
This integration focuses on reliability and security, utilizing WebSocket long-polling (长连接) to maintain a persistent connection between your local Openclaw gateway and the WeCom Open Platform. Whether you are looking to automate internal workflows or provide AI-driven support to employees, this skill provides a robust framework for enterprise-ready AI interactions.
WeCom Channel Integration Use Cases
- Deploying internal corporate AI assistants for employees on WeCom.
- Automating customer support or technical queries within WeCom group chats.
- Integrating Openclaw Skills into enterprise workflows without exposing local servers to the public internet.
- Providing a secure, managed chat interface for LLM interaction within a regulated business environment.
How WeCom Channel Integration Works
- The plugin establishes a secure WebSocket long-polling connection to the WeCom Open Platform using the provided Bot ID and Secret.
- When a user sends a message to the WeCom bot, the message is pushed through the WebSocket to the Openclaw gateway.
- Openclaw processes the input using the configured primary AI model defined in the agent defaults.
- The resulting AI response is sent back through the established channel, appearing as a reply in the user's WeCom interface.
- The gateway manages session states and access control policies (DMs and Group Chats) in real-time.
WeCom Channel Integration Setup
Follow these steps to enable the WeCom channel in your Openclaw Skills environment:
- Install the official plugin:
openclaw plugins install @wecom/wecom-openclaw-plugin
- Configure your
~/.openclaw/openclaw.jsonfile to enable the channel and plugin:
{
"channels": {
"wecom": {
"enabled": true,
"botId": "<YOUR_BOT_ID>",
"secret": "<YOUR_BOT_SECRET>",
"dmPolicy": "open",
"allowFrom": ["*"],
"groupPolicy": "open"
}
},
"plugins": {
"allow": ["wecom-openclaw-plugin"],
"entries": {
"wecom-openclaw-plugin": {
"enabled": true
}
}
}
}
- Restart the gateway to apply changes:
openclaw gateway restart
WeCom Channel Integration Data Schema & Taxonomy
The WeCom skill organizes its operational data and security boundaries through specific configuration keys within the Openclaw schema:
| Key | Description | Type |
|---|---|---|
dmPolicy |
Defines access for Direct Messages (pairing, open, allowlist, disabled) | String |
allowFrom |
A list of authorized User IDs or a wildcard "*" | Array |
groupPolicy |
Defines access for Group Chats (open, allowlist, disabled) | String |
groupAllowFrom |
A list of authorized Group IDs | Array |
botId / secret |
Authentication credentials from WeCom Open Platform | String |
sendThinkingMessage |
Toggle for the "thinking..." visual indicator | Boolean |
WeCom Channel Integration Advanced Features
- Multi-channel security: Restrict bot interactions to specific users or departments using the
allowlistdmPolicy. - Group Chat Isolation: Manage AI access in group settings via
groupAllowFromto ensure the bot only responds in approved environments. - Zero-Configuration Networking: Uses WebSocket long-polling to bypass NAT and firewall issues, ideal for self-hosted Openclaw Skills deployments.
- Thinking State Feedback: Enhances user experience by providing real-time "thinking" placeholders while the LLM generates a response.
SKILL.md
Loading
Related Openclaw Skills
Legal Concept Deep Dive
An expert legal analysis tool designed to clarify ambiguous or indeterminate legal concepts through legislative intent, judicial interpretation, and case boundaries.
Tavily Search
A high-performance web search skill that allows AI agents to retrieve real-time data and conduct online research via the Tavily API.
Agent Reach
Agent Reach provides AI agents with the ability to search, read, and interact across 14 major social and content platforms with zero-config setup.
Legal Evidence Mapping
A professional tool that translates complex legal statutes into actionable evidence checklists and burden of proof assignments.
minimax-image
A high-performance image generation skill leveraging the MiniMax API to deliver advanced text-to-image and image-to-image capabilities for AI agents.
ClawTeam
A powerful CLI orchestration tool for deploying and managing self-organizing AI agent swarms with built-in task dependencies and git isolation.
Featured*
