prose

Create and execute structured programs that orchestrate multi-agent workflows.

Updated Feb 12, 2026
One-click install
npx skills add https://github.com/sentientsprite/nemo-agent --skill prose-sentientsprite
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/sentientsprite/nemo-agent/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/sentientsprite/nemo-agent --skill prose-sentientsprite

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a structured programming language for orchestrating AI agents, turning complex multi-agent workflows into manageable, reproducible programs.

Core Features & Use Cases

  • Agent Orchestration: Define, configure, and manage multiple AI agents within a single program.
  • Workflow Automation: Automate complex tasks by sequencing, parallelizing, and controlling agent interactions.
  • 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 'examples/01-hello-world.prose' file.

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 syntax?▼

You can orchestrate multi-agent workflows by writing structured programs that define agent interactions and data flow using a declarative syntax. This approach supports agent definition, session management, and parallel execution to automate complex tasks.

Can I automate parallel execution and error handling for AI agents?▼

Yes, automating parallel execution and error handling for AI agents is supported. You can define structured programs that control agent interactions, manage data flow, and execute complex sequences with built-in error handling.

What is the best way to manage multiple AI agents in a single automated workflow?▼

The best way to manage multiple AI agents is using a structured programming language designed for agent orchestration. This allows you to define, configure, and sequence agent interactions within a reproducible program.

Do I need a specific framework to define agent sessions and loops for AI orchestration?▼

You do not need an external framework; this functionality provides the framework itself. It natively supports agent definition, session management, loops, and composition via imports to facilitate complex AI-driven systems.

How does composition via imports work for multi-agent systems?▼

Composition via imports works by allowing you to modularize and import structured programs into one another. This enables you to build complex multi-agent systems by combining smaller, manageable workflow definitions.

When should I use a declarative programming language for AI agent orchestration?▼

You should use a declarative programming language for AI agent orchestration when you need to turn complex, multi-agent workflows into manageable and reproducible programs, especially for tasks requiring parallel execution and error handling.