onebot-adapter

Connect OpenClaw to OneBot protocol for QQ bot integration. Use when receiving or sending QQ messages via NapCat or other OneBot servers.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "onebot-adapter" with this command: npx skills add haohaodlam/onebot-adapter-1-0-0

OneBot Adapter

Connect OpenClaw to OneBot protocol servers like NapCat for QQ bot functionality.

Quick Start

1. Configure Connection

Set OneBot server URL in environment or config:

export ONEBOT_WS_URL="ws://127.0.0.1:3001"
export ONEBOT_HTTP_URL="http://127.0.0.1:3000"
export ONEBOT_TOKEN="your-token"

2. Receive Messages

Use the WebSocket listener script to receive QQ messages:

python scripts/onebot_ws_listener.py

3. Send Messages

Use HTTP API to send messages:

from scripts.onebot_client import OneBotClient

client = OneBotClient()
client.send_private_msg(user_id=123456, message="Hello!")
client.send_group_msg(group_id=789012, message="Group message")

Connection Modes

WebSocket (Recommended)

  • Real-time bidirectional communication
  • Receives events instantly
  • Supports both sending and receiving

HTTP

  • Request-response model
  • Good for simple sending
  • Requires polling for receiving

Common Tasks

Get Login Info

client.get_login_info()

Get Friend/Group List

client.get_friend_list()
client.get_group_list()

Handle Messages

See references/message-handling.md for message parsing and response patterns.

NapCat Specific

NapCat is a OneBot11 implementation based on NTQQ.

Default ports:

  • WebSocket: 3001
  • HTTP: 3000
  • WebUI: 6099

Token authentication is optional but recommended for public deployments.

Troubleshooting

Connection refused: Check if OneBot server is running and ports are correct.

Authentication failed: Verify token matches OneBot server configuration.

Message not delivered: Check user_id/group_id exists and bot has permission.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Skill Editor

编辑、完善或审查 AgentSkills。当需要创建新技能、对现有 SKILL.md 进行修改、清理/审计/整理技能文件时激活此技能。触发词:编辑技能, skill 注意事项, metadata 检查, 完善技能, 清理技能, 审计技能, skill 规范, 编写 skill, 新建技能

Registry SourceRecently Updated
Automation

AgentYard

Autonomous agent marketplace — hire AI agents, pay in Lightning sats, get results delivered to email.

Registry SourceRecently Updated
Automation

Ai Agents Architect

Expert in designing and building autonomous AI agents. Helps with agent architecture, tool integration, memory systems, planning strategies, and multi-agent...

Registry SourceRecently Updated
Automation

Agent of Empires

Manage AI coding agent sessions via Agent of Empires (aoe)

Registry SourceRecently Updated