prose

Define and execute AI agent workflows using the OpenProse declarative language.

1|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/Justicegaines03/OpenClaw_NIST-AI-RMF_Compliance --skill prose-justicegaines03
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/Justicegaines03/OpenClaw_NIST-AI-RMF_Compliance/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/Justicegaines03/OpenClaw_NIST-AI-RMF_Compliance --skill prose-justicegaines03

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 exchange.

Core Features & Use Cases

  • AI Workflow Orchestration: Define sequences, parallel tasks, loops, and conditional logic for AI agents.
  • Agent Management: Define, configure, and manage specialized AI agents with specific models, skills, and permissions.
  • State Management: Persist and manage agent memory and execution state across sessions using files, SQLite, or PostgreSQL.
  • Use Case: Automate a code review process where one agent identifies issues, another suggests fixes, and a third synthesizes the feedback into a report.

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 AI agent workflows with complex control flow?

AI agent workflows are orchestrated using a declarative programming language to define sequences, parallel tasks, loops, and conditional logic, managing agent lifecycles and data exchange.

What is the best way to manage state persistence for AI agents across sessions?

State persistence for AI agents is managed across sessions using configurable backends, supporting filesystem, SQLite, and PostgreSQL to ensure robust and inspectable execution state.

Can I run multiple AI agents in parallel and handle errors in the same workflow?

Yes, multiple AI agents can execute in parallel with complex control flow patterns, including built-in error handling and loops, defined within a structured declarative program.

Does this workflow automation tool support PostgreSQL and SQLite backends?

Yes, the workflow automation tool supports filesystem, SQLite, and PostgreSQL as state backends, providing scalable and inspectable persistence for agent memory and execution state.

How do I automate a multi-agent code review process with specialized roles?

Automate a multi-agent code review by defining specialized agents with specific models and permissions, orchestrating them to identify issues, suggest fixes, and synthesize a report.