neo4j-getting-started-skill

Orchestrates zero-to-running-app in 8 stages — prerequisites → context → provision → model → load → explore → query → build. Each stage reads its own reference file. Supports HITL and fully autonomous operation. Use when starting a new Neo4j project from scratch, provisioning Aura, generating synthetic data, building a notebook or app, or running the full onboarding pipeline. Time budget ≤15 min autonomous, ≤90 min HITL. Does NOT cover Cypher query authoring — use neo4j-cypher-skill. Does NOT cover driver upgrades or Cypher migration — use neo4j-migration-skill. Does NOT cover CLI/admin tasks on an existing DB — use neo4j-cli-tools-skill.

1.64x

Quality

92%

Does it follow best practices?

Impact

84%

1.64x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Evaluation results

65%

20%

Setting Up a Neo4j E-Commerce Graph Project

Project skeleton setup with correct dependencies and schema

Criteria

Without context

With context

gitignore: .env entry

100%

gitignore: aura.env entry

100%

gitignore: .venv/ entry

100%

gitignore: neo4j-mcp entry

100%

neo4j-rust-ext in requirements

no standalone neo4j in requirements

100%

neo4j-viz in requirements

streamlit in requirements

100%

schema.json structure

100%

schema.cypher CYPHER 25 prefix

100%

schema.cypher IF NOT EXISTS

100%

schema.cypher constraints before indexes

100%

progress.md format

100%

progress.md context variables

100%

files in correct directories

100%

98%

49%

Building a Cypher Query Library for a Social Network Graph

Cypher query library authoring with correct syntax

Criteria

Without context

With context

CYPHER 25 on every query

100%

At least 5 queries

100%

At least 2 traversal queries

100%

LIMIT on read queries

20%

60%

EXISTS subquery used

100%

COUNT subquery used

60%

100%

Property access after aggregation

50%

100%

Correct param comment format

30%

100%

Node labels specified

90%

100%

queries directory used

100%

No GDS/APOC without confirmation

100%

No SQL-style comments

100%

90%

30%

Generating and Loading Synthetic Data for a Healthcare Graph

Synthetic data generation and batch import scripts

Criteria

Without context

With context

generate.py uses csv module

100%

generate.py needs no DB connection

100%

generate.py produces ≥200 patient rows

100%

import.py uses pandas DataFrame

100%

import.py uses driver.execute_query with rows

100%

Batch size 500

100%

MERGE not CREATE for nodes

100%

Nodes loaded before relationships

100%

MATCH endpoints before relationship MERGE

100%

load_dotenv used in import.py

100%

neo4j-rust-ext in requirements

python-dotenv in requirements

100%

Repository: neo4j-contrib/neo4j-skills
Commit: 6d44d31

Evaluated: 1 day ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Setting Up a Neo4j E-Commerce Graph Project Building a Cypher Query Library for a Social Network Graph Generating and Loading Synthetic Data for a Healthcare Graph

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.