knowledge-modeling

What problem does it solve?

This Skill helps you stop treating all structured ideas as interchangeable by choosing the knowledge-representation paradigm that best matches how you need to query, reason over, validate, and maintain your domain knowledge.

Core Features & Use Cases

• Guides representation-paradigm selection: knowledge graph, frames, semantic network, production rules, concept map, procedural knowledge/ontology (PKO), and hybrid approaches, with clear boundaries on when each fits.
• Teaches knowledge acquisition from tacit to explicit: elicit, articulate, formalize, validate against real scenarios, and encode so the result is actually usable by agents and systems.
• Defines validation + lifecycle: completeness, consistency, relevance, and currency checks paired with a Create → Validate → Publish → Use → Monitor → Update → Retire flow.
• Connects the theory to AI-agent systems: skills as frames, routing as production rules, memory as graph with freshness/drift properties, and context selection under token budgets.
• Explains GraphRAG patterns and when they win: entity-anchored retrieval, relationship-aware context, path reasoning, subgraph summarization, and hybrid vector+graph retrieval with rules to prevent “structure noise.”

Quick Start

Use knowledge-modeling to decide how to represent a domain so your agent can retrieve the right facts and relationships, then validate that choice against real scenarios.