ontology-builder-assistant

Derive evidence-backed ontologies from competency questions and sample data.

Updated Jul 23, 2026

Search Tags:#knowledge graph #ontology #data governance #graphrag #shacl #semantic modeling

Ready to run

npx skills add https://github.com/rahulgupta2018/agent-skills --skill ontology-builder-assistant

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ontology-builder-assistant
Source: https://github.com/rahulgupta2018/agent-skills/tree/main/skills/ontology-builder-assistant
Command: npx skills add https://github.com/rahulgupta2018/agent-skills --skill ontology-builder-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdflib, neo4j-graphrag, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the challenge of creating reusable, defensible, and enterprise-ready ontologies by enforcing a rigorous, evidence-based design workflow that prevents common modeling pitfalls like scope creep and lack of traceability.

Core Features & Use Cases

Evidence-Backed Modeling: Derives ontology structures directly from competency questions and sample data, ensuring every element is justified.
Enterprise-Grade Governance: Integrates critical dimensions like provenance, temporal validity, authority ranking, and jurisdiction tagging as first-class concerns.
Automated Artifact Generation: Automatically serializes models into Turtle/SHACL and generates GraphSchema JSON for immediate use in GraphRAG pipelines.

Quick Start

Activate the ontology-builder-assistant and provide your project requirements, competency questions, and sample data to begin the structured modeling workflow.

Frequently Asked Questions about ontology-builder-assistant

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

FAQPage Schema

How do I build an evidence-backed knowledge graph ontology from competency questions?▼

To build an evidence-backed knowledge graph ontology, you derive minimal ontology structures directly from purpose statements, competency questions, and sample data, ensuring every modeled element is fully traceable to its source evidence.

What is the best way to generate SHACL validation shapes for a semantic model?▼

The best way to generate SHACL validation shapes for a semantic model is to use an automated workflow that serializes evidence-backed ontology structures directly into Turtle/SHACL formats, satisfying enterprise requirements for stable IRIs and authority precedence.

Can I use rdflib with neo4j-graphrag for enterprise ontology design?▼

Yes, you can use rdflib with neo4j-graphrag for enterprise ontology design, as the workflow relies on these dependencies to derive semantic models, serialize Turtle artifacts, and generate GraphSchema JSON for GraphRAG pipelines.

How do I add data governance and provenance to a regulated enterprise knowledge graph?▼

To add data governance and provenance to a regulated enterprise knowledge graph, you integrate critical dimensions like temporal validity, authority ranking, and jurisdiction tagging as first-class concerns during the ontology derivation workflow.

Does GraphRAG require a GraphSchema JSON for information-extraction schemas?▼

GraphRAG pipelines utilize generated GraphSchema JSON artifacts to operationalize information-extraction schemas, automatically exporting these structures alongside serialized Turtle/SHACL files from the derived semantic models.

When should I not use automated ontology generation for semantic modeling?▼

You should not use automated ontology generation when you lack sample data or defined competency questions, because the workflow strictly derives minimal, evidence-backed structures to prevent scope creep and requires traceable inputs.