skills.rest
Sheldon-92
Sheldon-92COMMUNITY
Explore all skills by this author →
GitHub

agent-orchestration

Codify multi-agent orchestration rules into a reusable reference for agent runtimes.

3|Updated Sep 27, 2025
Search Tags:#multi-agent#agent orchestration#topology#human-in-the-loop#temporal#durable-execution#framework selection
One-click install
npx skills add https://github.com/Sheldon-92/TAD --skill agent-orchestration-sheldon-92
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-orchestration
Source: https://github.com/Sheldon-92/TAD/tree/main/.agents/skills/agent-orchestration
Command: npx skills add https://github.com/Sheldon-92/TAD --skill agent-orchestration-sheldon-92

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Agent orchestration is hard: coordinating multiple agents, frameworks, and tool permissions across runtimes without a consistent, validated design leads to miscoordination, drift, and unsafe executions.

Core Features & Use Cases

  • Framework-agnostic judgment rules for selecting orchestration approaches (LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK).
  • Clear topology guidance between Supervisor and Swarm, with HITL gating and durable execution patterns.
  • Tool-permission models and verifier gates to improve reliability in multi-agent tasks.

Quick Start

Describe your multi-agent task and preferred framework, then apply the agent-orchestration pack to select a topology, durability strategy, and tool-permission model.

Frequently Asked Questions about agent-orchestration

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

FAQPage Schema
How do I choose between Supervisor and Swarm topology for multi-agent workflows?▼

Multi-agent topology selection depends on your task coordination needs. This Skill provides validated judgment rules to choose between Supervisor and Swarm architectures, ensuring reliable agent coordination and safe tool execution across supported frameworks.

Does this provide guidance on selecting between LangGraph, CrewAI, and AutoGen for agent orchestration?▼

Yes, it offers framework-agnostic judgment rules for selecting orchestration approaches across LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, and Claude Agent SDK. It codifies framework choices based on your specific multi-agent task requirements and topology needs.

When do I need Temporal event sourcing instead of bare retries for durable execution?▼

Temporal event sourcing is needed for complex durable execution requiring robust state recovery. This Skill provides explicit guidance on when to use Temporal event sourcing versus bare retries, ensuring deterministic validation of durability requirements in multi-agent workflows.

How do I design human-in-the-loop interrupt and resume patterns for multi-agent systems?▼

Designing human-in-the-loop (HITL) patterns requires clear interrupt and resume gating. This Skill codifies HITL interrupt and resume designs alongside tool-permission models, ensuring reliable human oversight and deterministic validation in multi-agent orchestration.

What is the best way to manage tool permissions and verifier gates across multiple AI agents?▼

Managing tool permissions requires clear models and verifier gates to prevent unsafe executions. This Skill provides tool-permission models and verifier gates to improve reliability in multi-agent tasks, ensuring safe and validated tool usage across different runtimes.

Can I use this to orchestrate AI agents if I haven't selected a framework yet?▼

Yes, if you haven't selected a framework, it provides framework-agnostic judgment rules for choosing orchestration approaches. Describe your multi-agent task, and it helps you select the optimal framework, topology, and durability strategy.

Related Skills

Explore More Software Engineering Skills→
PaldomPaldom
1

instrumenting-with-mlflow-tracing

Instrument Python and TypeScript code with MLflow Tracing for LLM calls and agent decisions.

Community
Intermediate
jonnabiojonnabio
6

a2a-communication

Orchestrate agent communication and coordination within multi-agent topology schemas.

Community
Advanced
dotlab-hqdotlab-hq

langchain-middleware

Configure human-in-the-loop approval for LangChain tool calls with per-tool policies.

Official
Advanced
MattMaggMattMagg
3

Multi-Agent Orchestration

Generate coordinated routing and state-sharing patterns for multi-agent workflows across ADK, LangGraph, CrewAI, and OpenAI.

Community
Advanced