prose

Define and execute multi-agent workflows with a declarative programming language.

Updated Jan 26, 2026
One-click install
npx skills add https://github.com/coltonbatts/Loubot --skill prose-coltonbatts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/coltonbatts/Loubot/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/coltonbatts/Loubot --skill prose-coltonbatts

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex multi-agent workflows by allowing you to write structured programs that define agent behavior, data flow, and execution logic.

Core Features & Use Cases

  • Agent Orchestration: Define and manage multiple AI agents within a single program.
  • Structured Workflows: Create deterministic, repeatable processes for AI tasks.
  • Use Case: Automate a code review process where one agent identifies issues, another suggests fixes, and a third synthesizes the feedback into a report.

Quick Start

Use the prose skill to run the example program 'examples/01-hello-world.prose'.

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 workflows using a declarative programming language?

You orchestrate multi-agent workflows by writing declarative programs that define agent behavior, data flow, and execution logic. A virtual machine model manages agent lifecycles, context passing, parallel execution, and state persistence dynamically.

What is structured AI agent orchestration and when do I need it?

Structured AI agent orchestration coordinates multiple agents within deterministic, repeatable processes. You need it to automate complex multi-agent tasks, such as a code review process where agents identify issues, suggest fixes, and synthesize feedback.

How do I manage context passing and state persistence for parallel AI agents?

Context passing and state persistence for parallel AI agents are managed through a virtual machine model. This approach handles agent lifecycles and explicit control flow constructs to ensure deterministic execution across your multi-agent systems.

Can I dynamically compose AI agents using imports in my workflow automation?

Yes, you can dynamically compose AI agents via imports within your workflow automation. The declarative programming language supports explicit control flow constructs and dynamic agent composition to build flexible multi-agent systems.

What's the best way to create deterministic, repeatable processes for LLM orchestration?

The best way to create deterministic, repeatable processes for LLM orchestration is using a declarative programming language. It defines structured workflows that manage agent behavior and data flow, preventing unpredictable AI task execution.