ontology-generator

Generate InfraNodus ontology graphs in [[wikilinks]] syntax from topics or text.

3|Updated May 11, 2026

Search Tags:#knowledge graph #ontology #gap analysis #wikilinks #entity extraction #relationship modeling #infraNodus

Ready to run

npx skills add https://github.com/JeromyJSmith/lattice-platform --skill ontology-generator-jeromyjsmith

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ontology-generator
Source: https://github.com/JeromyJSmith/lattice-platform/tree/main/.agents/skills/skills-master/skill-ontology-creator
Command: npx skills add https://github.com/JeromyJSmith/lattice-platform --skill ontology-generator-jeromyjsmith

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts messy topics or source text into a structured ontology that can be visualized as a knowledge graph, helping you quickly surface entities, relationships, and rules without manually designing the network.

Core Features & Use Cases

Topic-based ontology generation: Create a comprehensive, non-tree network ontology for a given domain.
Text-based ontology extraction: Identify entities and relationship structure directly from user-provided text.
InfraNodus-ready wikilinks output: Produces graph statements in [[wikilinks]] syntax with explicit relation codes for immediate paste-and-visualize workflow.
Relationship balancing guidance: Encourages broad coverage across isA, partOf, hasAttribute, relatedTo, dependentOn, causes, locatedIn, occursAt, derivedFrom, and opposes.

Quick Start

Paste your domain topic or your source text and ask for an InfraNodus ontology graph in [[wikilinks]] syntax with balanced relationship codes.

Frequently Asked Questions about ontology-generator

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

FAQPage Schema

How do I convert text into a knowledge graph ontology?▼

You generate an ontology graph by extracting entities and relationships from your topic or source text and structuring them into a network using balanced relation codes like isA, partOf, and causes.

What is the best way to format entities for InfraNodus visualization?▼

Formatting entities for InfraNodus visualization requires emitting ontology lines in [[wikilinks]] syntax, ensuring each paragraph represents a relation with at least two linked entities and an allowed relation code.

Can I extract entity relationships directly from raw source text?▼

Yes, you can extract entity relationships directly from raw source text to identify the underlying relationship structure and map it into a non-tree network ontology for gap and cluster analysis.

Does InfraNodus ontology generation support gap and cluster analysis?▼

InfraNodus ontology generation supports gap and cluster analysis by structuring data as a comprehensive network rather than a hub-and-spoke tree, allowing you to surface structural gaps and relationship clusters.

What relation codes are available for relationship modeling in a knowledge graph?▼

Available relation codes for relationship modeling include isA, partOf, hasAttribute, relatedTo, dependentOn, causes, locatedIn, occursAt, derivedFrom, and opposes, ensuring broad coverage across the network ontology.

Why should I build a network ontology instead of a hub-and-spoke tree?▼

Building a network ontology instead of a hub-and-spoke tree is necessary for gap analysis and visualizing complex structural clusters, representing interconnected relationships accurately rather than forcing a rigid hierarchy.