skills.rest
moshehbenavraham
moshehbenavrahamCOMMUNITY
Explore all skills by this author →
Website𝕏@MoshehAvrahamGitHub

prose

Orchestrate multi-agent AI workflows with a VM-driven language.

2|Updated Jan 27, 2026
Search Tags:#ai#agents#orchestration#sessions#vm#openprose
One-click install
npx skills add https://github.com/moshehbenavraham/crocbot --skill prose
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/moshehbenavraham/crocbot/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/moshehbenavraham/crocbot --skill prose

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenProse provides a self-contained, VM-driven language to orchestrate AI agents, sessions, and workflows, turning ad-hoc prompts into reliable, repeatable automation.

Core Features & Use Cases

  • Structured orchestration: Define agents, sessions, blocks, and control flow to coordinate multi-step AI workflows.
  • Parallel and sequential execution: Seamlessly run tasks in parallel or in sequence with clear composition and context passing.
  • Persistent memory and state: Support for persistent agents and various state backends (filesystem, SQLite, PostgreSQL) to enable resumption and long-running tasks.
  • Modular program composition: Use imports, blocks, and pipelines to build scalable, reusable automation.
  • Subagent spawning via Task tool: Spawn real subagents to perform defined tasks and return binding pointers for downstream steps.

Real-world example: Coordinate a team of specialized agents (researcher, reviewer, writer) to gather, analyze, and synthesize insights, then produce a final report with traceable bindings and memory.

Quick Start

Install Crocbot and run a sample OpenProse program with prose run 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 multi-agent AI workflows with persistent state?▼

You can orchestrate multi-agent AI workflows with persistent state using a VM-driven language that defines agents, sessions, and blocks. This enables reliable coordination across long-running tasks with memory-enabled context passing.

What is the best way to run parallel AI agent tasks sequentially?▼

The best way to run parallel AI agent tasks sequentially is through structured orchestration using a VM-driven language. It allows seamless execution of tasks in parallel or sequence with clear composition and context passing.

Can I spawn subagents to perform specific tasks and pass results downstream?▼

Yes, you can spawn real subagents via a Task tool to perform defined tasks. The system returns binding pointers for downstream steps, enabling traceable context passing between specialized agents.

Does OpenProse support database-backed state like SQLite or PostgreSQL?▼

OpenProse supports database-backed state including SQLite and PostgreSQL, as well as local filesystem state. This enables workflow resumption and persistent memory for long-running multi-agent tasks.

How do I build reusable modular programs for AI session orchestration?▼

You build reusable modular programs for AI session orchestration using imports, blocks, and pipelines. This VM-driven approach allows scalable composition of multi-step workflows with structured control flow.

Related Skills

Explore More Software Engineering Skills→
MaxSaietsMaxSaiets

prose

Execute .prose programs with a VM-like runtime for multi-agent workflows.

Community
Advanced
nomad3nomad3

prose

Execute OpenProse .prose programs with a VM-style multi-agent orchestration model.

Community
Advanced
sakthiramsakthiram

multi-agent

Coordinate specialized agents to complete complex tasks with persistent sessions.

Community
Advanced
tamireslaeao-progtamireslaeao-prog

prose

Orchestrate multi-agent AI workflows from a single .prose program.

Community
Advanced