skills.rest
NJUxlj
NJUxljCOMMUNITY
Explore all skills by this author →
GitHub

prose

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

Updated Feb 1, 2026
Search Tags:#state management#agent workflow#multi-agent systems#ai orchestration#llm programming#prose language
One-click install
npx skills add https://github.com/NJUxlj/openclaw --skill prose-njuxlj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/NJUxlj/openclaw/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/NJUxlj/openclaw --skill prose-njuxlj

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 programmatically orchestrate AI agents, defining complex workflows with clear control flow, state management, and error handling, moving beyond simple chat interactions to build sophisticated AI-driven applications.

Core Features & Use Cases

  • Programmatic Agent Orchestration: Define multi-agent workflows using a structured language (.prose files).
  • State Management: Persist execution state via files, SQLite, or PostgreSQL for complex, long-running, or collaborative tasks.
  • Control Flow: Implement sequential execution, parallel processing, loops, conditionals, and error handling.
  • Use Case: Automate a code review process where one agent identifies issues, another suggests fixes, and a third synthesizes the feedback into a report, all managed by a .prose script.

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 multi-agent workflows with complex control flow?▼

Yes, it supports parallel processing, sequential execution, loops, conditionals, and error handling to structure complex multi-agent interactions.

Can I persist agent state for long-running tasks using SQLite or PostgreSQL?▼

Yes, execution state can be persisted via filesystem, SQLite, or PostgreSQL backends to support long-running and collaborative multi-agent tasks.

What is declarative AI orchestration and when do I need it for LLM programming?▼

Declarative AI orchestration uses structured programs to define agent interactions, needed when building sophisticated AI applications requiring clear control flow and state management beyond simple chats.

Does this multi-agent system support parallel execution and error handling?▼

Yes, the framework supports parallel execution, loops, conditionals, and error handling to manage complex control flow patterns in multi-agent systems.

Do I need a specific framework to run declarative agent workflow scripts?▼

No external framework dependencies are required; you define and execute workflows using structured scripts and supported backend storage for state persistence.

Related Skills

Explore More Software Engineering Skills→
ajshedivyajshedivy
4

agno-storage

Configure persistent storage backends for Agno agents and teams.

Community
Intermediate
artosetrovartosetrov

cdo

Orchestrate multi-agent workflows into phased execution plans with agent-bus communication.

Community
Advanced
agusmdevagusmdev
3

open-prose

Orchestrate multi-agent AI workflows with a declarative VM.

Community
Advanced
RachasumanthRachasumanth

prose

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

Community
Advanced