prose

Orchestrate OpenProse multi-agent workflows through a runtime VM.

1|Updated Mar 30, 2026
One-click install
npx skills add https://github.com/Arry8/openclaw-edge --skill prose-arry8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/Arry8/openclaw-edge/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/Arry8/openclaw-edge --skill prose-arry8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenProse's VM skill pack centralizes the orchestration of multi-agent workflows, enabling teams to define, execute, and monitor AI agent collaborations as structured programs without bespoke glue code.

Core Features & Use Cases

  • Unified runtime: Spawns and coordinates subagents via the Task tool, enabling parallel and nested executions.
  • Stateful execution: Documents and persists run state, imports, and agent memory through a consistent schema (filesystem or DB backends).
  • Modular composition: Supports imports, blocks, contexts, and pipelines for complex automation; great for production-grade workflows and rapid prototyping.
  • Activation triggers: Activates on prose commands, .prose files, or OpenProse mentions; ideal for interactive AI orchestration, tutorials, and automation pipelines.
  • Use cases: Designing multi-step AI workflows, testing orchestration patterns, or scaffolding agent-driven pipelines across teams.
  • Visualize complex orchestrations like captain’s chair patterns to coordinate parallel tasks.

Quick Start

Create a simple .prose workflow and run it with prose run your-workflow.prose to see the OpenProse VM orchestrate agents.

Frequently Asked Questions about prose

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

FAQPage Schema
How do I orchestrate parallel AI agents without writing custom glue code?

Multi-agent orchestration is centralized by mapping OpenProse concepts to a runtime VM, spawning subagents via the Task tool to execute parallel and nested workflows without bespoke integration code.

How does state management work for persistent multi-agent workflows?

State management for multi-agent workflows persists run state and agent memory through a consistent schema supporting filesystem, in-context, sqlite, and postgres backends across multiple runs.

Can I use .prose files to trigger automated agent pipelines?

Activation triggers support .prose files, prose commands, and OpenProse mentions, allowing you to define and execute automated agent pipelines by running the workflow file through the VM.

What is the best way to build multi-step AI workflows with imports and blocks?

Building multi-step AI workflows is achieved through modular composition, supporting imports, blocks, contexts, and pipelines to structure complex automation and production-grade agent-driven pipelines.

Does the OpenProse VM support nested agent execution for complex pipelines?

Nested agent execution is supported by the unified runtime VM, which coordinates subagents via the Task tool to enable both parallel and nested executions for complex orchestration patterns.