Verified:GitHub

prose

Interpret structured programs to orchestrate multi-agent AI workflows.

Updated Mar 31, 2026

Search Tags:#multi-agent workflow #structured programming #ai agent orchestration #ai session simulation #prose programming

Ready to run

npx skills add https://github.com/nuno7lopes/alisio --skill prose-nuno7lopes

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/nuno7lopes/alisio/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/nuno7lopes/alisio --skill prose-nuno7lopes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude-code, opus, haiku, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables the simulation of AI sessions using code, allowing users to orchestrate complex workflows involving multiple AI agents.

Core Features & Use Cases

Simulate AI Sessions: Write structured programs that mimic AI sessions and spawn subagents to perform tasks.
Multi-Agent Workflows: Design workflows that involve multiple AI agents working together.
Use Case: Imagine you want to create a workflow that combines code analysis, sentiment analysis, and bug detection. Use this Skill to define each agent's behavior and how they interact with each other.

Quick Start

Run the '01-hello-world.prose' example to see the basic structure of a Prose program in action.

Frequently Asked Questions about prose

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

FAQPage Schema

How do I orchestrate multi-agent AI workflows using structured code?▼

To orchestrate multi-agent AI workflows, you write structured programs that simulate AI sessions and define how agents interact. This Skill interprets those programs within a virtual machine to coordinate tasks like code analysis and bug detection.

What is AI session simulation and how does it work?▼

AI session simulation is the process of mimicking AI interactions through structured code. This Skill interprets your code to spawn subagents and execute tasks within a virtual machine, allowing modular composition of agent behaviors.

Do I need Claude Code to run multi-agent workflow simulations?▼

Yes, you need Claude Code or a similar AI framework to execute these multi-agent workflow simulations. The Skill relies on these frameworks to interpret the structured programs and manage the virtual machine operations.

Can I use different AI models in the same multi-agent workflow?▼

Yes, you can use different AI models in the same multi-agent workflow. The Skill supports modular composition of agents, allowing you to combine various models like Opus and Haiku for distinct tasks such as sentiment analysis or code generation.

How do I get started with simulating AI sessions in code?▼

To get started with simulating AI sessions, run the '01-hello-world.prose' example included in the Skill. This demonstrates the basic structure of a program and shows how to define agent behaviors and interactions.

What are the limitations of using structured programming for AI agent orchestration?▼

A limitation of using structured programming for AI agent orchestration is the dependency on specific frameworks like Claude Code to execute. Additionally, complex workflows require careful modular composition to avoid interaction conflicts between spawned subagents.