prose

Define and execute multi-agent workflows using the OpenProse programming language.

1|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/lachlanchen/LazyingArtBot --skill prose-lachlanchen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/lachlanchen/LazyingArtBot/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/lachlanchen/LazyingArtBot --skill prose-lachlanchen

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill allows you to define and execute complex multi-agent workflows using a structured, human-readable programming language, turning AI sessions into powerful, programmable computers.

Core Features & Use Cases

  • AI Workflow Automation: Define sequences, parallel tasks, loops, and error handling for AI agents.
  • Agent Orchestration: Manage multiple specialized AI agents (e.g., researchers, coders, critics) within a single program.
  • Use Case: Automate a code review process where one agent identifies potential bugs, another checks for style compliance, and a third synthesizes the feedback into a single report for the developer.

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 multiple AI agents in a structured workflow?

You orchestrate multiple AI agents by defining sequences, parallel execution, and loops in a structured programming language. This allows you to manage specialized agents within a single program for complex task automation.

What is multi-agent workflow automation and how does it handle errors?

Multi-agent workflow automation coordinates specialized AI agents using a structured language. It manages orchestration and includes error handling and state persistence to ensure reliable execution of complex AI sequences.

Can I run parallel AI tasks and pass dynamic context between agents?

Yes, you can run parallel AI tasks and pass dynamic context between agents. The system supports agent specialization and reusable blocks, enabling complex interactions within a multi-agent workflow.

How do I start automating a code review process with multiple AI agents?

You start by running an example program like '01-hello-world.prose'. This demonstrates how to define a sequence where one agent identifies bugs, another checks style, and a third synthesizes feedback.

Do I need specific dependencies to program AI agents with a structured language?

No external dependencies are required to program AI agents with this structured language. It operates through an AI VM that interprets the language directly within your AI sessions.

What are the limitations of using a structured language for AI orchestration?

Using a structured language for AI orchestration requires learning specific syntax for loops, parallel execution, and state management. It is designed for complex, programmable automation rather than simple single-turn prompts.