multiagent

Automate OpenClaw multi-agent Telegram lifecycle tasks via shell orchestration with jq.

6|2|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/rikouu/openclaw-multiagent --skill multiagent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multiagent
Source: https://github.com/rikouu/openclaw-multiagent/tree/main
Command: npx skills add https://github.com/rikouu/openclaw-multiagent --skill multiagent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes scripts (resource) and references (resource) components.

What problem does it solve?

By packaging the multi-agent Telegram group setup into scripted operations, this skill prevents the silent failures that happen when openclaw.json subsystems fall out of sync and everyone suffers from the wrong bot responding or agents not seeing each other.

Core Features & Use Cases

  • Team-wide lifecycle automation: commands add and remove agents, rebuild bindings, update account settings, and restart the gateway without hand-editing JSON.
  • Safety and diagnosis: the doctor command validates bindings, account tokens, mention patterns, allow lists, and workspace files, while clear-sessions forces agents to reload new instructions.
  • Metadata-driven workspace sync: managed templates keep AGENTS.md, SOUL.md, and USER.md consistent so every agent knows how to respond to messages and other agents.

Quick Start

Trigger the multiagent skill with /multiagent list all agents to inspect the current bot roster and health.

Frequently Asked Questions about multiagent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage multiple Telegram bots in an OpenClaw group without editing JSON directly?

You can manage multiple Telegram bots by running shell commands that automate agent lifecycle tasks, applying correct bindings, telegram accounts, and allow lists to the OpenClaw configuration without manual JSON editing.

Why does the wrong Telegram bot respond in my multi-agent OpenClaw workspace?

The wrong bot responds when openclaw.json subsystems fall out of sync, causing silent failures in agent bindings and mention patterns that allow incorrect agents to intercept messages.

How do I diagnose and troubleshoot broken Telegram agent bindings in OpenClaw?

You diagnose broken Telegram agent bindings by running the doctor command, which validates bindings, account tokens, mention patterns, allow lists, and workspace files to identify configuration mismatches.

Do I need jq installed to automate OpenClaw multi-agent Telegram configurations?

Yes, you need jq installed because the skill relies on shell orchestration with jq to parse and modify the JSON configurations that control multi-agent Telegram group setups.

What is the best way to add a new agent to an existing OpenClaw Telegram group?

The best way to add a new agent is using the add command, which automatically rebuilds bindings, updates account settings, and syncs workspace metadata like AGENTS.md before restarting the gateway.

How do I force OpenClaw agents to reload new instructions after updating workspace metadata?

You force agents to reload new instructions by running the clear-sessions command, which resets agent states and ensures every bot reads the updated AGENTS.md, SOUL.md, and USER.md files.