decision-support

Convert user descriptions into ontology-backed decision graphs for quadstore persistence and ZMQ rule export.

32|3|Updated Sep 30, 2025
One-click install
npx skills add https://github.com/BulloRosso/etienne --skill decision-support-bullorosso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-support
Source: https://github.com/BulloRosso/etienne/tree/main/skill-repository/standard/optional/decision-support
Command: npx skills add https://github.com/BulloRosso/etienne --skill decision-support-bullorosso

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Transforms natural-language descriptions into structured, ontology-grounded decision graphs that can be persisted in a quadstore, visualized as interactive diagrams, and exported as executable ZeroMQ rule sets.

Core Features & Use Cases

  • Ground user inputs into ontologized decision graphs with triggers, conditions, actions, and outcomes.
  • Persist graphs in a quadstore and render them for review and modification, with optional LLM prompts for actions.
  • Export rules to the ZeroMQ execution layer and integrate with a Node.js-based workflow.

Quick Start

Describe a situation in plain language in the chat panel to generate a first-draft decision graph.

Frequently Asked Questions about decision-support

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn natural language chats into ontology-driven decision graphs?

You can convert natural language chats into ontology-driven decision graphs by grounding user descriptions into structured nodes with triggers, conditions, and actions. This requires a live ontology snapshot to map chat context into structured logic.

Can I export decision graphs as ZeroMQ rule sets for Node.js?

Yes, you can export decision graphs as ZeroMQ rule sets for Node.js. The system persists graphs in a quadstore and exports the derived rules to a ZeroMQ execution layer for automated workflow reasoning.

Do I need a live ontology snapshot to build decision graphs from chat?

Yes, building decision graphs from chat requires a live ontology snapshot. The ontology provides the structural grounding needed to derive conditions and actions from user descriptions and map them into the quadstore.

How do I persist and visualize decision graphs in a quadstore?

You persist decision graphs in a quadstore by using the system's derivation and persistence endpoints. Once stored, the graphs can be rendered as interactive diagrams for review and modification.

Can I attach LLM prompts to actions in a decision graph?

Yes, you can attach optional LLM prompts to actions within a decision graph. This allows the workflow to generate dynamic responses or trigger automated reasoning when specific actions are executed.