A comprehensive framework for creating custom AI agents and integrating them into Feishu messaging environments using Openclaw Skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install create-feishu-agent-skill
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 create-feishu-agent-skill 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 Feishu Agent Integration?
This skill provides a standardized workflow for deploying specialized AI agents within the Feishu (Lark) ecosystem. By utilizing Openclaw Skills, developers can define complex agent personalities through a structured file system, managing everything from core behavioral principles to long-term memory. The integration bridges the gap between large language models and enterprise communication, allowing for seamless automated interactions within team chats and private messages.
The core value of this skill lies in its ability to transform a standard AI model into a context-aware teammate. By configuring specialized personas like health managers or technical experts, Openclaw Skills enable organizations to scale internal support and project management through intelligent, reactive bots that live directly where the team communicates.
Feishu Agent Integration Use Cases
- Deploying specialized corporate assistants (e.g., Technical Support, HR Helpdesk) directly into Feishu group chats.
- Creating automated health and wellness monitors that track team activity and provide data-driven interventions.
- Building project-specific agents that maintain a persistent memory of discussions and task statuses across multiple threads.
- Setting up reactive bots that monitor specific keywords or events in Feishu to trigger automated workflows.
How Feishu Agent Integration Works
- Define the agent identity by creating a dedicated workspace with files like SOUL.md and AGENTS.md to establish personality and rules.
- Register a custom application on the Feishu Open Platform to generate the necessary App ID and App Secret.
- Configure IM permissions and event subscriptions (such as im.message.receive_v1) to allow the agent to interact with users.
- Update the global Openclaw configuration file to map the Feishu channel credentials to the local agent workspace.
- Establish bindings that link the specific Feishu account to the designated agent ID for message routing.
- Launch or restart the Openclaw gateway to establish a websocket connection for real-time message processing.
Feishu Agent Integration Setup
First, create the agent directory structure in your local environment:
mkdir -p ~/.openclaw/workspace/agents/<agent_name>
touch ~/.openclaw/workspace/agents/<agent_name>/{SOUL.md,IDENTITY.md,AGENTS.md,MEMORY.md}
Next, configure your ~/.openclaw/openclaw.json with your Feishu App credentials and bind the agent to the channel. Finally, restart the service:
openclaw gateway restart
Feishu Agent Integration Data Schema & Taxonomy
The skill utilizes a hierarchical Markdown-based file system to manage agent state and configuration within the Openclaw Skills framework:
| File | Role | Content Description |
|---|---|---|
| SOUL.md | Personality | Defines core truths, responsibilities, operational boundaries, and 'vibe'. |
| AGENTS.md | Logic | Defines trigger conditions and local workspace inheritance rules. |
| IDENTITY.md | Identification | Stores the specific name and identity markers for the agent. |
| MEMORY.md | Context | Manages long-term historical data and interaction logs. |
| openclaw.json | Integration | Contains the channel settings (AppID, Secret) and agent-to-channel bindings. |
Feishu Agent Integration Advanced Features
- Support for Websocket connection mode, ensuring low-latency communication without needing a public callback URL.
- Configurable group policies that allow agents to observe and participate in group chats without requiring direct @mentions.
- Multi-agent binding capabilities, allowing a single Feishu bot to be powered by different AI personalities depending on the configuration.
- Integration with diverse LLM providers (e.g., GLM, MiniMax) through the unified Openclaw Skills interface.
SKILL.md
Loading
Related Openclaw Skills
Agent Training System
A comprehensive framework for onboarding, supervising, and evolving multi-agent teams to ensure mission alignment and behavioral consistency.
Writing Skills
A framework that applies Test-Driven Development principles to documentation, ensuring AI agents follow patterns and techniques reliably.
Writing Plans
A systematic blueprinting tool for AI agents to generate granular, TDD-focused implementation plans before writing code.
Verification Before Completion
A rigorous technical protocol that mandates fresh evidence from tests and builds before any work is claimed as finished.
WeChat Publisher
Automate the publication of articles and management of drafts on WeChat Official Accounts using these Openclaw Skills.
Email Marketing & Intelligent Auto-Reply
A robust automation skill for personalized bulk email marketing and intelligent, FAQ-driven automated replies.
Featured*
