teams

Manage persistent AI agents with shared memory, tasks, and notifications.

14|6|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/jholhewres/devclaw --skill teams-jholhewres
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teams
Source: https://github.com/jholhewres/devclaw/tree/main/pkg/devclaw/copilot/builtin/skills/teams
Command: npx skills add https://github.com/jholhewres/devclaw --skill teams-jholhewres

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a structured system for running persistent AI agents that share memory, coordinate tasks, and communicate so teams can maintain stateful workflows and avoid duplicated work or lost context.

Core Features & Use Cases

  • Team orchestration: create, list, update, and delete teams and agents to model persistent roles.
  • Task and workflow management: assign, track, and transition tasks through inbox → assigned → in_progress → review → done with blocking and cancellation states.
  • Shared memory & communication: save facts and documents to shared memory, run standups, and send comments, direct messages, and notifications for cross-agent coordination.
  • Use Case: run an agent heartbeat cycle that checks mentions, loads working state, pulls assigned tasks, updates progress, notifies stakeholders, and clears state when complete.

Quick Start

Use the teams skill to create a team, add a persistent agent named siri, assign it a task, and save a shared fact so agents can coordinate.

Frequently Asked Questions about teams

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

FAQPage Schema
How do I coordinate persistent AI agents with shared memory?

To coordinate persistent AI agents with shared memory, you can create teams, assign and track tasks through state transitions, save shared facts, and send inter-agent notifications to maintain stateful workflows without losing context.

How do I assign and track tasks across multiple AI agents?

You assign and track tasks using a workflow state machine that transitions items through inbox, assigned, in_progress, review, and done states, while supporting blocking and cancellation for cross-agent coordination.

What is an agent heartbeat cycle for team coordination?

An agent heartbeat cycle is a routine that checks mentions, loads working state, pulls assigned tasks, updates progress, notifies stakeholders, and clears state upon completion to keep persistent agents synchronized.

Can I run standups and send direct messages between AI agents?

Yes, you can run standups and send direct messages between AI agents. The system provides communication actions for sending comments, direct messages, and notifications to facilitate cross-agent coordination.

What APIs are available for team orchestration and shared memory management?

Available APIs include team_manage, team_agent, team_task, team_memory, and team_comm. These actions allow you to create, list, get, update, and delete resources while managing working state and notifications.