Skill32.8k estrellas del repoactualizado 5d ago

agent-management

The agent-management Claude Code skill enables creation, configuration, and lifecycle management of multiple AI agents through the AI Maestro CLI framework. Use this skill when users request agent operations such as creating new agents, listing existing ones, hibernating or waking agents, managing plugins, or performing any other agent lifecycle tasks like deletion, renaming, or state export/import.

Ver fuente Repositorio: claude-code-templates

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/agent-management && cp -r /tmp/agent-management/cli-tool/components/skills/ai-maestro/agent-management ~/.claude/skills/agent-management

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# 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](https://github.com/23blocks-OS/ai-maestro) suite.

## Prerequisites

Requires [AI Maestro](https://github.com/23blocks-OS/ai-maestro) running locally with tmux 3.0+.

```bash
# 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

| Command | Description |
|---------|-------------|
| `aimaestro-agent.sh list` | List 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> --confirm` | Delete 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

| Command | Description |
|---------|-------------|
| `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

| Command | Description |
|---------|-------------|
| `aimaestro-agent.sh export <agent>` | Export agent config |
| `aimaestro-agent.sh import <file>` | Import agent from file |

## Usage Examples

```bash
# 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

| Status | Meaning |
|--------|---------|
| `online` | Running in tmux session |
| `offline` | Registered but no active session |
| `hibernated` | Saved state, session killed |

## Full AI Maestro Experience

This skill is part of the [AI Maestro](https://github.com/23blocks-OS/ai-maestro) platform, which provides **6 skills** for AI agent orchestration: messaging, memory, docs, graph, planning, and agent management.

Del mismo repositorio

agent-evaluationSkill

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

agent-expertSubagent

Use this agent when creating specialized Claude Code agents for the claude-code-templates components system. Specializes in agent design, prompt engineering, domain expertise modeling, and agent best practices. Examples: <example>Context: User wants to create a new specialized agent. user: 'I need to create an agent that specializes in React performance optimization' assistant: 'I'll use the agent-expert agent to create a comprehensive React performance agent with proper domain expertise and practical examples' <commentary>Since the user needs to create a specialized agent, use the agent-expert agent for proper agent structure and implementation.</commentary></example> <example>Context: User needs help with agent prompt design. user: 'How do I create an agent that can handle both frontend and backend security?' assistant: 'Let me use the agent-expert agent to design a full-stack security agent with proper domain boundaries and expertise areas' <commentary>The user needs agent development help, so use the agent-expert agent.</commentary></example>

agent-manager-skillSkill

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

agent-memory-mcpSkill

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

agent-memory-systemsSkill

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

agent-messagingSkill

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.

agent-tool-builderSkill

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa

ai-agents-architectSkill

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling.