prose

Orchestrates AI agents and manages their state with declarative control-flow programs.

16|1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/Flexasaurusrex/OpenPaw --skill prose-flexasaurusrex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/Flexasaurusrex/OpenPaw/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/Flexasaurusrex/OpenPaw --skill prose-flexasaurusrex

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex AI workflows by allowing you to write structured programs that orchestrate multiple AI agents, manage their state, and control their execution flow.

Core Features & Use Cases

  • AI Workflow Orchestration: Define multi-agent tasks using a declarative language.
  • Agent Management: Define, configure, and manage AI agents with specific models, prompts, and permissions.
  • Control Flow: Implement sequences, parallel execution, loops, error handling, and conditional logic for AI tasks.
  • Use Case: Automate a code review process where one agent identifies issues, another suggests fixes, and a third generates a summary report, all coordinated by a master program.

Quick Start

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

Frequently Asked Questions about prose

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

FAQPage Schema
How do I orchestrate multiple AI agents in a structured workflow?

You orchestrate multiple AI agents by defining structured programs using a declarative language that manages agent state and controls execution flow for complex multi-agent workflows.

Can I implement parallel execution and conditional logic for AI agent tasks?

Yes, you can implement parallel execution, loops, error handling, and conditional logic for AI tasks by defining control flow patterns within the declarative programming language.

What is the best way to automate a multi-step code review process with AI agents?

Automate a code review process by writing a structured program where one agent identifies issues, another suggests fixes, and a third generates a summary report, all coordinated by a master program.

Do I need a specific environment to run multi-agent systems with declarative programming?

Yes, you need a Prose Complete system capable of spawning subagents and managing state to execute the structured programs that orchestrate multiple AI agents.

How does agent specialization work when orchestrating AI workflows?

Agent specialization works by defining, configuring, and managing individual AI agents with specific models, prompts, and permissions within the declarative orchestration program.

What are the limitations of using declarative language for AI orchestration?

The declarative language requires a Prose Complete system to spawn subagents and manage state, meaning it cannot execute multi-agent workflows or specialized agent tasks without that underlying environment.