skills.rest
SafeAI-Lab-X
SafeAI-Lab-XCOMMUNITY
Explore all skills by this author →
GitHub

prose

Coordinates multi-agent workflows with sessions, blocks, and pluggable state backends.

1.0k|59|Updated Mar 20, 2026
Search Tags:#workflow#agents#orchestration#state-management#vm#openprose
One-click install
npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill prose-safeai-lab-x
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/SafeAI-Lab-X/ClawKeeper --skill prose-safeai-lab-x

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenProse provides a unified, VM-driven framework for coordinating multiple AI agents, enabling reproducible, end-to-end workflows across sessions, blocks, and imports within OpenClaw ecosystems.

Core Features & Use Cases

  • Coordinates multi-agent workflows using sessions, blocks, and parallel constructs with explicit context passing.
  • Supports pluggable state backends (filesystem, SQLite, PostgreSQL) to persist, resume, and audit runs.
  • Enables common orchestration patterns such as captain-patterns, reusable blocks, and cross-agent pipelines in production-grade safety tooling.

Quick Start

Activate by loading prose.md and this SKILL.md, then define a small workflow that invokes a session and observes coordinated results.

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 deterministic state management?▼

You orchestrate multi-agent workflows by loading the skill pack into an OpenClaw ecosystem, which uses a VM-driven framework to coordinate sessions and blocks with explicit context passing and traceable state.

Can I persist and resume multi-agent workflow runs across different databases?▼

Yes, multi-agent workflow runs support pluggable state backends for filesystem, SQLite, or PostgreSQL, allowing you to persist, resume, and audit execution states across different storage systems.

What orchestration patterns are supported for coordinating AI agents?▼

Supported AI agent orchestration patterns include captain-patterns, reusable blocks, and cross-agent pipelines, enabling structured workflow routing and safe cross-agent coordination.

How does context passing work when coordinating multiple AI agents in a workflow?▼

Context passing in multi-agent workflows is explicit, managed through the VM-driven framework that coordinates sessions and blocks to ensure safe and traceable cross-agent coordination.

Do I need an OpenClaw ecosystem to run multi-agent workflow orchestration?▼

Yes, the multi-agent workflow orchestration operates within OpenClaw ecosystems, coordinating sessions, blocks, and imports through its VM-driven skill pack.

What is the best way to structure reproducible end-to-end AI agent pipelines?▼

The best way to structure reproducible AI agent pipelines is using a VM-driven framework that coordinates sessions and blocks with pluggable state backends for auditable, end-to-end workflows.

Related Skills

Explore More Software Engineering Skills→
frankhli843frankhli843

prose

Orchestrate multi-agent AI workflows through a VM-like scripting surface.

Community
Advanced
zyj18860969891-bytezyj18860969891-byte

prose

Orchestrate multi-agent AI workflows with parallel blocks and persistent memory.

Community
Advanced
agusmdevagusmdev
3

open-prose

Orchestrate multi-agent AI workflows with a declarative VM.

Community
Advanced
jxtngxjxtngx
2

deep-agents-memory

Route agent memory operations across ephemeral and persistent storage backends.

Community
Advanced