Knowledge Graph Builder

This builds knowledge graphs that connect entities through relationships, which helps AI systems reason about connections and verify facts instead of hallucinating. You get ontology design patterns, entity extraction from unstructured text, and hybrid graph-vector search that combines semantic similarity with relationship traversal. The skill covers Neo4j, Neptune, ArangoDB, and TigerGraph selection based on your scale needs. The emphasis on confidence scoring for every relationship and aggressive entity deduplication is smart, since merged duplicates and reliability filtering are what separate useful graphs from noisy ones. Best for domains where relationships matter more than raw documents, like fraud detection or recommendation engines.

skills.sh installs: 217
GitHub stars: 21
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add oakoss/agent-skills --skill knowledge-graph-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

Knowledge Graph Builder

Overview

Knowledge graphs make implicit relationships explicit, enabling AI systems to reason about connections, verify facts, and reduce hallucinations. They combine structured entity-relationship modeling with semantic search for powerful knowledge retrieval.

When to use: Complex entity relationships central to the domain, verifying AI-generated facts against structured knowledge, semantic search combined with relationship traversal, recommendation systems, fraud detection, or pattern recognition.

When NOT to use: Simple tabular data (use a relational database), purely document-based search with no relationships (use the rag-implementer skill), read-heavy workloads with no traversal needs, or when the team lacks graph modeling expertise. For KB architecture selection and governance, use the knowledge-base-manager skill.