Neo4j Agent Skills

Neo4j Agent Skills is a collection of installable knowledge packages for AI agents — Claude Code, Cursor, Cline, Gemini CLI, Codex, and any other Agent Skills-compatible tool.

Browse and install at skills.sh/neo4j-contrib/neo4j-skills.

npx skills add neo4j-contrib/neo4j-skills
For Claude Code, Gemini CLI, and Codex-specific install commands, see Installing Neo4j Agent Skills.

Skills bundle step-by-step instructions, reference documentation, and executable scripts into a progressive disclosure model: the agent loads only what it needs, keeping context usage minimal while ensuring correct, Neo4j-specific behavior.

Available Skills

neo4j-getting-started-skill

A Claude Code skill that takes you from zero to a running graph application in a single session. Invoke it with /neo4j-getting-started-skill and a plain-language description — the skill collects any missing context and then runs 8 stages automatically: prerequisites → context → provision → model → load → explore → query → build.

/neo4j-getting-started-skill fraud detection for a fintech startup
/neo4j-getting-started-skill Healthcare patient journey analysis, intermediate Python dev,
local Docker, synthetic data, Jupyter notebook please.

Database targets: aura-free, aura-pro, local-docker, local-desktop, existing-cloud

Data sources: synthetic, demo, csv, documents (GraphRAG via neo4j-graphrag)

App types: notebook, streamlit, fastapi, graphrag, mcp, explore-only

When all six context variables are provided upfront the skill runs fully autonomously (⇐15 min local, ⇐25 min with Aura provisioning). It writes progress.md after each stage and resumes automatically if interrupted.

Prerequisites: Claude Code, Python >= 3.10, Docker (only for local-docker).

npx skills add neo4j-contrib/neo4j-skills/neo4j-getting-started-skill

neo4j-cypher-skill

Write, optimize, and debug Cypher queries. Covers Cypher 25 syntax, query planning, indexes, and common patterns.

AI agents trained on older data frequently generate deprecated Cypher. The patterns below are deprecated or replaced in Neo4j 2025.x — prefer the Cypher 25 equivalents.
Deprecated (4.x / 5.x) Cypher 25 replacement

shortestPath((a)-[*]-(b))

SHORTEST 1 (a)-[*]-(b)

()-[*1..5]-() variable-length

Quantified path: ()-[]{1,5}-()

CALL { …​ } IN TRANSACTIONS

CALL { …​ } IN TRANSACTIONS OF N ROWS

WITH collect(x) AS …​ subquery workaround

COLLECT { MATCH …​ RETURN …​ }

WITH count(*) AS …​ subquery workaround

COUNT { MATCH …​ }

RETURN existsn)-[:R]→(

RETURN exists { (n)-[:R]→() }

For driver API deprecations, see neo4j-migration-skill.

npx skills add neo4j-contrib/neo4j-skills/neo4j-cypher-skill

All Skills by Category

Querying and Modeling

Skill When to use

neo4j-cypher-skill

Write, optimize, and debug Cypher queries. Covers Cypher 25 syntax, query planning, indexes, and common patterns.

neo4j-modeling-skill

Design and review graph data models. Covers node/relationship patterns, property choices, and relational-to-graph migration.

neo4j-getting-started-skill

Zero-to-app walkthrough: provision → model → load → query. Use for first-time setup on Aura or Docker.

Importing Data

Skill When to use

neo4j-import-skill

Load structured data (CSV, JSON) via LOAD CSV, neo4j-admin import, and the Data Importer GUI.

neo4j-document-import-skill

Extract knowledge graphs from unstructured documents and PDFs using SimpleKGPipeline.

neo4j-migration-skill

Upgrade drivers and Cypher from 4.x/5.x to 2025.x. Covers API changes, deprecated functions, and Cypher 25 syntax.

AI and Search

Skill When to use

neo4j-vector-index-skill

Create and query vector indexes for semantic similarity search. Covers index creation, embedding ingestion, and ai.text.embed().

neo4j-genai-plugin-skill

In-Cypher LLM integration via ai.text.* functions: embeddings, text completion, structured output, chat, and pure-Cypher GraphRAG.

neo4j-graphrag-skill

Build GraphRAG retrieval pipelines with neo4j-graphrag. Covers retriever selection, retrieval_query patterns, and LangChain/LlamaIndex integration.

neo4j-agent-memory-skill

Graph-native agent memory: short-term (conversations), long-term (POLE+O entity model), and reasoning traces. Covers neo4j-agent-memory, MCP, LangChain, CrewAI, ADK.

neo4j-mcp-skill

Set up and use the Neo4j MCP server for tool-based agent access to the database.

Graph Data Science

Skill When to use

neo4j-gds-skill

Run graph algorithms (PageRank, Louvain, node embeddings) on self-managed Neo4j using GDS.

neo4j-aura-graph-analytics-skill

Run GDS-compatible graph algorithms on Neo4j Aura via the Graph Analytics API.

Drivers

Skill When to use

neo4j-driver-python-skill

Python driver: execute_query, sessions, transactions, async, UNWIND batching, data types.

neo4j-driver-javascript-skill

JavaScript/TypeScript driver: executeQuery, managed transactions, RxJS, data types.

neo4j-driver-java-skill

Java driver: ExecutableQuery, managed/explicit transactions, object mapping, reactive.

neo4j-driver-dotnet-skill

.NET/C# driver: ExecuteReadAsync/ExecuteWriteAsync, DI registration, IResultCursor.

neo4j-driver-go-skill

Go driver: ExecuteQuery, generic helpers, spatial types, connection configuration.

Frameworks and Platforms

Skill When to use

neo4j-graphql-skill

Build GraphQL APIs backed by Neo4j using @neo4j/graphql. Covers type definitions, @relationship, @cypher, and filtering.

neo4j-spring-data-skill

Spring Boot + Neo4j with Spring Data Neo4j: @Node, @Relationship, repositories, projections.

neo4j-cli-tools-skill

DB admin via neo4j-admin, cypher-shell, and aura-cli. Covers backups, imports, user management, and Aura provisioning.

neo4j-aura-provisioning-skill

Create and manage Neo4j Aura instances via the Aura CLI and REST API. Covers async polling, credential handling, and tier selection.

Usage

Once installed, skills activate automatically. Describe your task in plain language and the agent selects and loads the appropriate skill:

"Update these Cypher queries for Neo4j 2026"          -> neo4j-cypher-skill
"Upgrade our Python driver to the latest version"     -> neo4j-migration-skill
"Import this CSV file into Neo4j"                     -> neo4j-import-skill
"Build a GraphRAG pipeline over our document corpus"  -> neo4j-graphrag-skill
"Run PageRank on the graph"                           -> neo4j-gds-skill
"/neo4j-getting-started-skill fraud detection"        -> neo4j-getting-started-skill

Skills use a three-level progressive disclosure model. The agent loads a short description (~50 tokens) first, then the full protocol (~2,000 tokens) only when the skill is needed, and selectively loads deep reference files on demand — minimizing context usage across a long session.

Related Resources