New to Claude Skills? Learn how to install them →

davila7 on GitHub

AI Maestro Agent Management

Free

Efficiently manage AI agents through a unified CLI.

Get this skill

Free · Opens the source repo

What AI Maestro Agent Management does

AI Maestro Agent Management provides a command-line interface (CLI) for creating, managing, and orchestrating multiple AI agents. It streamlines the entire agent lifecycle, allowing users to create, hibernate, wake, rename, and manage plugins for their agents. This skill is designed for developers and designers who need to handle AI agents efficiently, whether for testing, development, or deployment purposes.

The CLI supports a variety of commands that facilitate agent management. Users can easily list all agents and their statuses, create new agents with specific tasks and tags, and perform updates or deletions as needed. The ability to hibernate agents helps save system resources when they are not in use, and waking them up is straightforward, allowing for quick resumption of work. Additionally, the skill includes commands for exporting and importing agent configurations, making it easier to back up or migrate agent setups.

For those looking to extend the functionality of their agents, the plugin management commands allow for easy installation and uninstallation of plugins. Users can also manage plugin sources through a marketplace, providing flexibility in how agents can be enhanced. This skill is particularly useful in environments where multiple AI agents are in operation and need to be managed cohesively.

Overall, AI Maestro Agent Management is an essential tool for anyone looking to leverage AI agents effectively within their projects. By simplifying the management process, it allows users to focus more on development and less on the overhead of maintaining agent states and configurations.

When to use it

Use this skill when you need to create, manage, or orchestrate AI agents efficiently through a command-line interface.

When not to use it

This skill may not be suitable for users who prefer graphical interfaces or those not using the AI Maestro platform.

What you can build with it

Creating a New Agent

Quickly create a new AI agent for a specific task using the command line, specifying its directory and tags.

Managing Agent States

Hibernate agents at the end of the day to save resources and wake them up the next morning for continued work.

Backup Agent Configurations

Export agent configurations before making significant changes to ensure you can restore them if needed.

How to install AI Maestro Agent Management

View source

1. Install with the skills CLI

npx skills add davila7/claude-code-templates/agent-management --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by davila7

AI Maestro Agent Management

Create, manage, and orchestrate multiple AI agents through a unified CLI. Handles the full agent lifecycle: create, hibernate, wake, rename, export/import, and plugin management. Part of the AI Maestro suite.

Prerequisites

Requires AI Maestro running locally with tmux 3.0+.

# Install the CLI
git clone https://github.com/23blocks-OS/ai-maestro-plugins.git
cd ai-maestro-plugins && ./install-agent-cli.sh

Core Commands

Agent Lifecycle

CommandDescription
aimaestro-agent.sh listList all agents with status
aimaestro-agent.sh show <agent>Detailed agent information
aimaestro-agent.sh create <name> --dir <path>Create new agent
aimaestro-agent.sh update <agent> --task "..."Update task/tags
aimaestro-agent.sh delete <agent> --confirmDelete agent
aimaestro-agent.sh rename <old> <new>Rename agent
aimaestro-agent.sh hibernate <agent>Save state, free resources
aimaestro-agent.sh wake <agent>Resume hibernated agent
aimaestro-agent.sh restart <agent>Hibernate then wake

Plugin Management

CommandDescription
aimaestro-agent.sh plugin install <agent> <plugin>Install plugin
aimaestro-agent.sh plugin uninstall <agent> <plugin>Remove plugin
aimaestro-agent.sh plugin list <agent>List installed plugins
aimaestro-agent.sh plugin marketplace add <agent> <source>Add marketplace

Export/Import

CommandDescription
aimaestro-agent.sh export <agent>Export agent config
aimaestro-agent.sh import <file>Import agent from file

Usage Examples

# Create a backend API agent
aimaestro-agent.sh create backend-api \
  --dir ~/projects/backend \
  --task "Build REST API with TypeScript" \
  --tags "api,typescript"

# End of day -- save resources
aimaestro-agent.sh hibernate frontend-ui
aimaestro-agent.sh hibernate data-processor

# Resume next morning
aimaestro-agent.sh wake frontend-ui --attach

# Install a plugin on an agent
aimaestro-agent.sh plugin install backend-api my-plugin

# Backup before risky changes
aimaestro-agent.sh export backend-api -o backup.json

Agent Statuses

StatusMeaning
onlineRunning in tmux session
offlineRegistered but no active session
hibernatedSaved state, session killed

Full AI Maestro Experience

This skill is part of the AI Maestro platform, which provides 6 skills for AI agent orchestration: messaging, memory, docs, graph, planning, and agent management.

Frequently asked questions about AI Maestro Agent Management

Similar skills