prose

Activate and compose multi-agent workflows within the OpenProse runtime.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/Jnuso/OpenClaw --skill prose-jnuso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/Jnuso/OpenClaw/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/Jnuso/OpenClaw --skill prose-jnuso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenProse provides a cohesive runtime and language for coordinating AI agents, sessions, imports, and persistent state across runs. This Skill unit bundles the OpenProse VM semantics, skill activation, onboarding, and a standardized structure for integrating extensions, so developers can rapidly define, discover, and compose agent-driven workflows.

Core Features & Use Cases

  • Unified activation and onboarding for OpenProse skills, ensuring consistent entry points and discovery.
  • Standardized frontmatter (name, description) at SKILL.md root, plus optional resources (scripts/references/assets) for on-demand behavior.
  • Seamless integration with state backends (filesystem, SQLite, PostgreSQL, in-context) through the skill's guidance documentation.
  • Clear guidance for composing modular workflows with agents, sessions, imports, and memory, enabling scalable automation across projects.
  • Use cases include building reusable orchestration patterns, managing long-running workflows, and enabling cross-skill interoperability.

Quick Start

Install and load the OpenProse VM skill, then activate the prose skill unit to begin orchestrating a simple multi-agent workflow.

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 persistent state across runs?

Multi-agent workflow orchestration with persistent state requires a runtime that coordinates agents, sessions, and state backends. This skill provides a unified VM runtime to define, initialize, and connect agent-driven workflows with consistent discovery and resource organization.

What is the best way to structure reusable AI agent skills for cross-project interoperability?

Structured agent skills require standardized frontmatter with name and description at the root, plus optional directories for scripts, references, and assets. This approach enforces consistent entry points and on-demand behavior for scalable cross-project automation.

Can I use SQLite or PostgreSQL as a state backend for long-running agent sessions?

SQLite and PostgreSQL state backends are supported for long-running agent sessions. This skill provides integration guidance for filesystem, SQLite, PostgreSQL, and in-context state management to maintain persistent memory across workflow runs.

How do I onboard and activate new skills within a multi-agent runtime?

Skill onboarding and activation within a multi-agent runtime uses structured initialization to register agents and sessions. This skill unit bundles VM semantics to ensure standardized entry points, consistent discovery, and seamless composition of modular workflows.

Does multi-agent orchestration work without external dependencies for state management?

Multi-agent orchestration operates without external dependencies by using in-context or filesystem state backends. This skill bundles its own VM runtime semantics, requiring no external packages to define, initialize, and connect agents for basic workflow composition.

Why do my agent workflow sessions lose state between separate automated runs?

Agent workflow sessions lose state without a configured persistent state backend. This skill addresses the problem by providing integration guidance for filesystem, SQLite, PostgreSQL, and in-context state management to maintain memory across separate runs.