Data Graph Database
Use when the user asks about Neo4j and Cypher, Amazon Neptune, Gremlin, JanusGraph, SPARQL/RDF stores, graph traversal performance or knowledge graph storage. Produces graph model, queries and indexing and scaling choices. Not for relational/graph schema theory (use data-modeling) or GraphRAG prompting (use prompt-rag-query-design).
Install
npx skills add j4flmao/agent-skills --skill data-graph-databasegit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/data/graph-database ~/.claude/skills/data-graph-databasePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Data Graph Database ## Purpose Design graph data models for connected domains (social networks, recommendation engines, knowledge graphs, fraud detection) with optimal traversal patterns, platform selection, and scaling strategy. ## Agent Protocol ### Trigger Exact user phrases: "Neo4j", "Amazon Neptune", "JanusGraph", "graph database", "graph model", "Cypher", "Gremlin", "RDF", "SPARQL", "graph traversal", "property graph", "knowledge graph", "graph schema", "node label", "relationship", "graph query". ### Input Context Before activating, verify: - Domain data (nodes, relationships, properties, cardinality) - Query patterns (depth of traversal, path enumeration, aggregations) - Transaction volume (reads/sec, writes/sec, complexity) - Consistency requirements (ACID vs CQRS) - Existing graph platform or greenfield - Integration points (existing databases, streaming, ML pipelines) - Expected graph size (millions, billions of nodes/edges) ### Output Artifact Graph data model with node labels, relationship types, traversal patterns, and platform-specific deployment config. ### Response Format ```cypher // Neo4j schema + constraints + traversal queries ``` ```groovy // Gremlin traversals for Neptune/JanusGraph ``` ```yaml # JanusGraph storage backend config # Neptune cluster config ``` No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick. ### Completion Criteria
Details
- Skill name
data-graph-database- Repository
- j4flmao/agent-skills
- Path
skills/data/graph-database/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Data Graph Database skill do?
Use when the user asks about Neo4j and Cypher, Amazon Neptune, Gremlin, JanusGraph, SPARQL/RDF stores, graph traversal performance or knowledge graph storage. Produces graph model, queries and indexing and scaling choices. Not for relational/graph schema theory (use data-modeling) or GraphRAG prompting (use prompt-rag-query-design).
How do I install the Data Graph Database skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill data-graph-database. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Data Graph Database popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Data Lineage
45j4flmao/agent-skills
Use when the user asks about data lineage, OpenLineage, Marquez, column-level lineage, impact analysis of a schema change or data provenance. Produces lineage collection setup (Airflow provider, dbt-ol, Spark listener), storage and impact queries. Not for catalog search and glossary (use data-data-catalog).
Data Distributed Storage
45j4flmao/agent-skills
Use when the user asks about HDFS, S3, ADLS, GCS, MinIO or Ceph for data workloads, replication and erasure coding, small-file problems, storage tiering or lifecycle policies. Produces storage backend choice, layout and durability and cost settings. Not for database storage engines (use database-internals-mechanics) or file formats (use data-formats).
Data Nosql Database
45j4flmao/agent-skills
Use when the user asks about MongoDB, Cassandra, DynamoDB single-table design, Cosmos DB, Couchbase, partition keys, GSIs, consistency levels or NoSQL denormalization. Produces database choice, access-pattern-driven data model and capacity settings. Not for graph databases (use data-graph-database) or Redis caching (use backend-caching).
Browse the most popular Claude skills, all databases skills, or write your own with the skills generator.