prose

Coordinate OpenProse VM workflows to automate multi-agent orchestration.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenProse provides a self-contained Skill unit for orchestrating AI agent workflows within the OpenProse VM. It enables activation via SKILL.md frontmatter, defines runtime mapping, and supports optional resources (scripts/references/assets) to extend capability.

Core Features & Use Cases

  • Spawns subagents via the Task tool to run sessions and coordinate tasks
  • Manages imports, persistent agents, and memory for long-running workflows
  • Supports parallel execution, loops, blocks, and context passing across skill boundaries

Quick Start

OpenProse SKILL ready: run prose run <path-to-your-program.prose> to execute a program that uses this 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 AI workflows with persistent memory?

To orchestrate multi-agent AI workflows with persistent memory, you can use the OpenProse VM to spawn subagents, manage persistent agents, and coordinate long-running sessions across multiple state backends like filesystem, SQLite, and PostgreSQL.

Can I run parallel execution and loops across multiple AI agents?

Yes, you can run parallel execution and loops across multiple AI agents. The OpenProse VM supports blocks, loops, and context passing across skill boundaries to coordinate complex, parallel task execution.

What state backends are supported for AI agent session management?

Supported state backends for AI agent session management include the filesystem, in-context storage, SQLite, and PostgreSQL. These options enable persistent agents and memory for end-to-end automation pipelines.

How do I execute a program that uses an OpenProse skill?

To execute a program that uses an OpenProse skill, run the command 'prose run <path-to-your-program.prose>' in your terminal. This activates the workflow defined by the SKILL.md frontmatter and starts the orchestrated agent tasks.

Do I need specific dependencies to automate multi-agent orchestration pipelines?

No specific dependencies are required to automate multi-agent orchestration pipelines using this skill. It operates as a self-contained unit within the OpenProse VM, utilizing optional scripts, references, and assets to extend its runtime capabilities.

What is the best way to manage long-running AI agent workflows?

The best way to manage long-running AI agent workflows is by using a VM that supports persistent agents and memory. The OpenProse VM coordinates these long-running workflows by passing context across skill boundaries and utilizing durable state backends.