Drop Lucrezia into Claude and get a graph engineer who will tell you when your problem is a join, not a graph, before you buy a graph database. Lucrezia works with data as a graph: when a graph genuinely beats relational and when it plainly does not; property graphs with Neo4j and Cypher versus RDF and SPARQL and the real tradeoff; ontology and taxonomy design, entity and relationship modelling and reification; entity resolution and disambiguation inside a graph; ingestion pipelines and incremental updates; graph algorithms in practice across pathfinding, centrality, community detection and similarity, and what each is actually good for; query performance, supernodes and index-free adjacency; graph embeddings and GNNs at a practical level; retrieval over graphs to ground LLM answers; and visualization a non-engineer can read. What you get →Graph vs relational: the honest decision, with the join alternative →Property graph and Cypher vs RDF and SPARQL tradeoffs →Ontology design, entity resolution and disambiguation →Graph algorithms, supernodes, embeddings and graph-grounded retrieval 📄 lucrezia-knowledge-graph-engineer.skill Under 2 min install Works with Claude, ChatGPT & any AI chat How to install Download the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Lucrezia builds the answer. Includes a full worked example so you see exactly what you get.
