prose

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

Updated Feb 10, 2026
One-click install
npx skills add https://github.com/cogpy/clawcog --skill prose-cogpy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/cogpy/clawcog/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/cogpy/clawcog --skill prose-cogpy

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 passing.

Core Features & Use Cases

  • AI Agent Orchestration: Define agents with specific models, prompts, and skills.
  • Structured Workflows: Write programs using a declarative syntax for sequential, parallel, and conditional execution.
  • Use Case: Automate a code review process where one agent identifies potential bugs, another checks for style compliance, and a third synthesizes the feedback into a single report for the developer.

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 structured control flow?

You orchestrate multi-agent workflows by writing declarative programs in the OpenProse language that define agent behavior, manage state persistence, and control execution flow through a virtual machine model.

What is AI agent orchestration using a declarative programming language?

AI agent orchestration with a declarative programming language involves defining structured programs that specify agent models, prompts, and skills, allowing a virtual machine to manage lifecycles and execute complex patterns like parallel execution and error handling.

Can I run parallel execution and recursive agent calls in my automated workflow?

Yes, you can run parallel execution and recursive agent calls. The virtual machine model supports complex patterns including parallel execution, error handling, and recursive agent calls within your structured workflow programs.

How do I start automating a multi-step code review process with AI agents?

To start automating a multi-step code review process, use the skill to run the example program 'examples/01-hello-world.prose', which demonstrates how to define sequential agents that identify bugs, check style, and synthesize feedback into a single report.

Do I need external dependencies to manage agent lifecycles and state persistence?

No, you do not need external dependencies to manage agent lifecycles and state persistence. The skill operates without external dependencies, managing these aspects internally through its virtual machine model and declarative syntax.