AI Multi Agent Systems
Use when the user asks about a multi-agent system in LangGraph, AutoGen, CrewAI or OpenAI Agents SDK handoffs, shared blackboard state, A2A, checkpointing or human approval in an agent graph. Produces a runtime design: typed state, nodes, routing, durable checkpointer, interrupts, budgets and tracing. Not for choosing the topology (use multi-agent-topology).
Install
npx skills add j4flmao/agent-skills --skill ai-multi-agent-systemsgit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/ai/multi-agent-systems ~/.claude/skills/ai-multi-agent-systemsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Multi-Agent Systems
## Purpose
Implement and operate systems where several specialized agents cooperate. The engineering problems are classic distributed-systems problems wearing an LLM costume: shared state, message contracts, termination, retries, durability across human waits, and tracing. Prefer deterministic orchestration (explicit graph) for production; use dynamic conversational orchestration only where flexibility is worth the unpredictability.
## Agent Protocol
### Trigger
"multi-agent", "LangGraph supervisor", "AutoGen", "CrewAI", "agent handoff", "shared state between agents", "blackboard", "agent approval step", "A2A", "agents talking to each other".
### Input Context
- Roles already decided (or the topology skill output).
- Framework constraints and language.
- Which nodes touch production state; approval owners.
- Durability needs (can a run wait hours/days for a human?).
### Output Artifact
Runtime design and code skeleton: state schema, nodes, routing, checkpointer, interrupts, budgets, tracing.
### Response Format
```
Orchestration: {graph|conversation|handoff} Framework: {name@version}
State schema: {TypedDict/Pydantic fields + reducers}
Nodes: {agent/tool nodes} Routing: {conditional edges}
Durability: checkpointer={postgres|sqlite|memory}, thread_id={key}
HITL: interrupt before {nodes}
Budgets: recursion_limit={n}, tokens={n}, timeout={s}
Tracing: {backend}
```
### Completion CriteriaDetails
- Skill name
ai-multi-agent-systems- Repository
- j4flmao/agent-skills
- Path
skills/ai/multi-agent-systems/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the AI Multi Agent Systems skill do?
Use when the user asks about a multi-agent system in LangGraph, AutoGen, CrewAI or OpenAI Agents SDK handoffs, shared blackboard state, A2A, checkpointing or human approval in an agent graph. Produces a runtime design: typed state, nodes, routing, durable checkpointer, interrupts, budgets and tracing. Not for choosing the topology (use multi-agent-topology).
How do I install the AI Multi Agent Systems skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill ai-multi-agent-systems. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Multi Agent Systems popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Data Data Lakehouse
45j4flmao/agent-skills
Use when the user asks about lakehouse architecture, choosing Iceberg or Delta for our lakehouse, medallion bronze/silver/gold layers, Databricks Unity Catalog, Delta Sharing, Apache Paimon or multi-engine catalogs (Polaris, Glue). Produces layer design, catalog and access model and format commitment. Not for single-table operations (use data-data-lake).
AI Agentic Workflows
45j4flmao/agent-skills
Use when the user asks about an agentic workflow, prompt chaining, router, orchestrator-workers, evaluator-optimizer, ReAct, plan-and-execute or a LangGraph workflow with human checkpoints. Produces the simplest workflow pattern with typed state, loop bounds and approval points. Not for multi-agent runtimes (use ai-multi-agent-systems) or single-loop mechanics (use ai-agent-core-loop).
Data Data Strategy
45j4flmao/agent-skills
Use when the user asks about data strategy, data vision, data maturity assessment, data operating model (centralized, federated, hybrid), data culture or data literacy. Produces a maturity assessment, strategic pillars and a governance roadmap. Not for data mesh implementation (use data-data-mesh) or governance policy (use enterprise-data-governance).
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.