skills.rest
NicolaiLassen
NicolaiLassenCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

compose-agents

Compose Python multi-agent pipelines with sequential, parallel, and loop primitives.

19|6|Updated Mar 12, 2026
Search Tags:#parallel execution#multi-agent#orchestration#agent routing#Python#iterative loop#sequential workflow
One-click install
npx skills add https://github.com/NicolaiLassen/orxhestra --skill compose-agents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: compose-agents
Source: https://github.com/NicolaiLassen/orxhestra/tree/main/docs/skills/compose-agents
Command: npx skills add https://github.com/NicolaiLassen/orxhestra --skill compose-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you design reliable multi-agent workflows by coordinating when one agent runs after another, when multiple agents run simultaneously, and when an iterative review/repair loop should continue.

Core Features & Use Cases

  • SequentialAgent: Chain agents so the next agent uses the previous agent’s final output as context.
  • ParallelAgent: Run multiple agents concurrently with branch isolation, then combine results downstream.
  • LoopAgent: Repeat a set of agents until a stop condition is met, supporting fixed iteration limits or custom continuation logic.
  • Transfer routing: Hand off work between specialized sub-agents using transfer tools, enabling triage and delegation patterns.

Quick Start

Use compose-agents to build a pipeline that runs research in parallel, then synthesizes the results sequentially, and finally reviews the draft in an approval loop.

Frequently Asked Questions about compose-agents

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

FAQPage Schema
How do I orchestrate multiple agents in a Python pipeline?▼

You orchestrate multiple agents in a Python pipeline by using composition primitives to chain sequential steps, where the next agent uses the previous agent's final output as context. This allows reliable multi-agent workflow coordination.

Can I run multiple agents in parallel and combine their results?▼

Yes, you can run multiple agents concurrently with branch isolation using parallel execution primitives. This enables parallel analysis workflows where multiple agents run simultaneously and combine results downstream.

How do I create an iterative review loop for agent drafting and repair?▼

You create an iterative review loop by repeating a set of agents until a stop condition is met, supporting fixed iteration limits or custom continuation logic for iterative drafting and review until an approval threshold is reached.

What is the best way to route tasks to specialized sub-agents in Python?▼

The best way to route tasks to specialized sub-agents is using transfer routing via tools to hand off work between agents. This enables triage and delegation patterns for multi-agent orchestration.

Do I need any external dependencies to use multi-agent orchestration patterns?▼

No external dependencies are required to use these multi-agent orchestration patterns. The composition primitives provide SequentialAgent, ParallelAgent, and LoopAgent capabilities directly for Python workflows.

Related Skills

Explore More Software Engineering Skills→
hotriluanhotriluan
3

google-adk-python

Build and orchestrate Python-based AI agents with hierarchical coordination and tool integration.

Community
Basic
WenyuChiouWenyuChiou
23

agent-output-reconciler

Reconcile multi-agent task outputs into a structured report with recommended actions.

Community
Advanced
MattMaggMattMagg
3

ADK Orchestration

Design deterministic multi-agent orchestration workflows with SequentialAgent, ParallelAgent, and LoopAgent.

Community
Advanced
ormastesormastes
1

agents

Orchestrate iterative agent loops and team coordination across MCP tools.

Community
Advanced