skill CX Codex

multi-agent-orchestration — Claude Code skill: how to install

Q: How do I install multi-agent-orchestration in Claude Code?

Run `npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a claude-code` in your terminal. You can also place the skill file directly at `~/.claude/skills/multi-agent-orchestration/SKILL.md`.

Guides the architecture of multi-agent setups, delegating specialized roles and combining outputs. Helpful for multi-stage workflows across multiple LLMs.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a claude-code

Open on GitHub

What multi-agent-orchestration does

This skill guides how to structure teams of cooperating agents. It includes reference implementations in examples/orchestration_patterns.py for pipeline flows, concurrent runs, manager delegation, and consensus loops. Framework boilerplates for CrewAI, AutoGen, LangGraph, and Swarm live inside examples/framework_implementations.py.

Support code sits in the scripts/ directory. You get agent_communication.py for shared state and message brokers, workflow_management.py for task execution, and benchmarking.py to evaluate efficiency. Keep in mind that running these Python scripts requires installing each respective framework dependency locally. That makes setting up your virtual environment the immediate first step.

What it helps with

Coordinate agents in hierarchical structures with a manager lead
Run concurrent research tasks and aggregate outputs into one report
Implement message bus and shared state across Python agent modules
Build stateful multi-step pipelines with LangGraph or CrewAI

Example prompts for the agent

Create a CrewAI team where a researcher passes findings to a report writer
How do I build a consensus voting pattern across multiple agents in AutoGen?
Set up a LangGraph state graph with parallel steps and error recovery

How to install multi-agent-orchestration

1Skills CLI (Vercel)

npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a claude-code

2Manually: put the files in place

~/.claude/skills/multi-agent-orchestration/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/multi-agent-orchestration/

1Skills CLI (Vercel)

npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a codex

2Manually: put the files in place

.agents/skills/multi-agent-orchestration/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a cursor

2Manually: put the files in place

.cursor/skills/multi-agent-orchestration/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install qodex-ai/ai-agent-skills multi-agent-orchestration

2Manually: put the files in place

.github/skills/multi-agent-orchestration/SKILL.md

1Skills CLI (Vercel)

npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a gemini-cli

2Platform CLI

gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/multi-agent-orchestration

Manually: put the files in place

.devin/skills/multi-agent-orchestration/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about multi-agent-orchestration

How do I install multi-agent-orchestration in Claude Code?

Run npx skills add qodex-ai/ai-agent-skills --skill multi-agent-orchestration -a claude-code in your terminal. You can also place the skill file directly at ~/.claude/skills/multi-agent-orchestration/SKILL.md.

What agent orchestration patterns does this skill cover?

It provides patterns for sequential execution, parallel workers, manager-led hierarchies, consensus debate, and tool-mediated coordination.

Which multi-agent frameworks are included in the examples?

The repository provides code templates for CrewAI, Microsoft AutoGen, LangGraph, and OpenAI Swarm in examples/framework_implementations.py.

agent-orchestration OrchestKit A skill of patterns for autonomous agent loops, multi-agent coordination and multi-scenario runs. Useful when you build agent pipelines and pick a framework. CX Codex +1 1,400installs open-multi-agent-orchestration reason-machines A skill that teaches your agent to build AI agent teams on the open-multi-agent TypeScript framework: roles, models, task dependencies. CX Codex +1 710installs crewai davila7 Designs multi-agent teams on CrewAI: roles, tasks, orchestration and process types. Useful once a single agent stops being enough. 141installs agents-crewai Orchestra Research A Claude skill for assembling teams of autonomous agents with roles, memory, and sequential or hierarchical task execution. 371installs skypilot-multi-cloud-orchestration Orchestra Research Orchestrates ML training and batch workloads across 20+ clouds while cutting GPU expenses through spot auto-recovery and region selection. CX Codex +1 944installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 349,800installs

From the same set3

word-document-processor A skill for .docx work: extract text, build documents from scratch, and edit existing files with tracked changes. Useful when the agent has to touch someone else's contract. CX Codex +1 3,600installs financial-analysis-agent Helps build agents for fundamental stock evaluation and risk calculation. Practical for developing robo-advisors or investment trackers. CX Codex +1 1,300installs