prose

Defines multi-agent workflows with structured control flow and state persistence.

Updated Jul 17, 2026
One-click install
npx skills add https://github.com/kolbick/Kolb-Bot --skill prose-kolbick
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prose
Source: https://github.com/kolbick/Kolb-Bot/tree/main/extensions/open-prose/skills/prose
Command: npx skills add https://github.com/kolbick/Kolb-Bot --skill prose-kolbick

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and examples (resource) components.

What problem does it solve?

This Skill automates complex multi-agent workflows by allowing you to write structured programs that define agent interactions, control flow, and state management.

Core Features & Use Cases

  • Agent Orchestration: Define and manage multiple AI agents within a single workflow.
  • Structured Control Flow: Implement sequences, parallel execution, loops, and conditional logic for deterministic AI operations.
  • Use Case: Automate a code review process where one agent identifies potential bugs, another checks for style guide adherence, and a third synthesizes the feedback into a single report for the developer.

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 multiple AI agents in a structured workflow?

You orchestrate multiple AI agents by writing declarative programs that define agent interactions, control flow, and state management. This approach manages agent definitions, session spawning, and parallel execution within a single structured workflow.

What is the best way to automate complex multi-agent workflows with conditional logic?

Automating complex multi-agent workflows is best handled through declarative programming that implements sequences, parallel execution, loops, and conditional logic. This structured control flow ensures deterministic AI operations across multiple specialized agents.

Can I define agent specialization and permissions for multi-agent systems?

Yes, you can define agent specialization through model selection and configure specific permissions. This allows you to manage distinct agent roles, such as separating bug identification from style guide adherence, within the same orchestration program.

Does this multi-agent orchestration approach support state persistence and error handling?

State persistence and error handling are supported natively within the structured syntax. You can manage session states, handle execution errors, and maintain workflow continuity across complex multi-agent loops and parallel processes.

How do I compose and reuse multi-agent workflow definitions across different programs?

You compose and reuse multi-agent workflow definitions through import statements within the declarative programming language. This allows you to modularize agent definitions and orchestration logic, importing them into new structured programs as needed.