prose

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

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/clsdavid/autocrab --skill prose-clsdavid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/clsdavid/autocrab/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/clsdavid/autocrab --skill prose-clsdavid

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, control flow, and data passing.

Core Features & Use Cases

  • Agent Orchestration: Define custom agents with specific models, prompts, and skills.
  • Structured Control Flow: Implement sequential, parallel, and conditional execution logic.
  • Use Case: Automate a code review process where one agent identifies issues, another suggests fixes, and a third summarizes the findings, all orchestrated by a central program.

Quick Start

Run the 'hello world' example program using the prose skill.

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 structured programs that define agent behavior, control flow, and data passing. This approach manages agent lifecycles and handles sequential, parallel, and conditional execution logic.

Can I run parallel and sequential tasks in an AI agent orchestration program?

Yes, you can run parallel and sequential tasks in AI agent orchestration by implementing structured control flow. This allows you to define conditional execution logic and manage data passing between specialized agents.

What is agent specialization in multi-agent systems?

Agent specialization in multi-agent systems is defining custom agents with specific models, prompts, and skills. This allows a central program to orchestrate distinct roles, such as identifying issues, suggesting fixes, and summarizing findings.

How do I handle state persistence for automated AI orchestration workflows?

You handle state persistence for automated AI orchestration workflows through various configured backends. This manages agent lifecycles and ensures data passing is maintained across complex, structured program executions.

Does the declarative language for LLM programming support program composition?

Yes, the declarative language for LLM programming supports program composition via imports. This enables you to modularize complex multi-agent workflows and combine structured programs to automate large-scale processes.