graph-engineer_skill

Overview

This skill is a knowledge-graph engineering specialist focused on entity modeling and causal relationship design for graph databases like Neo4j and FalkorDB. It helps architects and engineers build scalable, debuggable graphs by enforcing entity resolution, edge cardinality, temporal validity, and query profiling. Use it to design schemas, diagnose performance issues, and operationalize causal graphs.

How this skill works

The skill inspects graph schema and data to find anti-patterns: high-degree nodes, missing constraints, weak entity resolution, and absent temporal metadata on edges. It reviews Cypher queries and execution plans to highlight expensive traversals and suggests rewrites, index strategies, and cardinality limits. For causal modelling, it validates edge semantics and temporal ordering to avoid spurious links and recommends structure changes to make causal inference tractable.

When to use it

• Designing a production knowledge graph or migrating to Neo4j/FalkorDB
• Diagnosing slow Cypher queries or unexplained performance regressions
• Resolving duplicate entities and establishing robust entity resolution pipelines
• Modeling causal relationships with clear temporal validity and edge semantics
• Preparing graphs for scale: preventing god-node and over-connection failures

Best practices

• Do entity resolution first — canonicalize identities before expanding the graph
• Limit node degree with explicit cardinality caps and alternative aggregation nodes
• Attach temporal validity to edges from the start; avoid retroactive-only timestamps
• Profile every query with EXPLAIN (or the DB profiler) and iterate on plans
• Favor sparse, purposeful connectivity over dense linking; add edges only for required queries
• Enforce constraints and indexes early to prevent runaway data quality issues

Example use cases

• Design a customer 360 graph with deduplicated person entities and activity edges capped by source
• Rework a graph with a god node by inserting intermediate aggregation nodes and degree limits
• Review and refactor slow Cypher queries using profile output and recommended rewrites
• Model an incident-cause graph where edges carry timestamps and confidence scores for causal analysis
• Validate entity-resolution rules and provide deterministic merge strategies for ambiguous matches