Neo4j Getting Started Skill
Run the official eight-stage Neo4j pipeline from prerequisites through provision, model, load, explore, query, and build a runnable app or notebook.
Overview
Neo4j Getting-Started Skill is an agent skill most often used in Build (also Validate scope) that runs an 8-stage zero-to-running-app Neo4j onboarding pipeline with per-stage reference files.
Install
npx skills add https://github.com/neo4j-contrib/neo4j-skills --skill neo4j-getting-started-skillWhat is this skill?
- 8 ordered stages: prerequisites → context → provision → model → load → explore → query → build
- Loads one reference file per stage only—not the entire doc set at once
- Supports HITL (≤90 min) and fully autonomous runs (≤15 min time budget)
- Integrates Neo4j MCP (read/write Cypher, schema, GDS) and data-modeling validate/visualize tools
- Explicitly excludes deep Cypher authoring, driver migration, and CLI admin—points to sibling Neo4j skills
- 8 sequential onboarding stages from prerequisites through build
- ≤15 min autonomous time budget and ≤90 min HITL budget documented
- Skill version 0.3.0
Adoption & trust: 1 installs on skills.sh; 80 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You want a new Neo4j project but lack a ordered path from Aura setup through modeled data to something you can query and demo.
Who is it for?
Indie devs or agents spinning up a first Neo4j Aura app, synthetic dataset, or notebook with MCP-guided Cypher and modeling checks.
Skip if: Migrating existing drivers, advanced Cypher-only tutoring, or admin tasks on a long-running production cluster without the full onboarding arc.
When should I use this skill?
Starting a new Neo4j project from scratch, provisioning Aura, generating synthetic data, building a notebook or app, or running the full onboarding pipeline.
What do I get? / Deliverables
You complete provisioned Aura (or equivalent), a validated graph model, loaded data, explored results, and a built app or notebook within the documented time budget.
- Provisioned Neo4j instance and validated graph model
- Loaded dataset with explore/query walkthrough
- Runnable notebook or minimal application
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Zero-to-running graph app is primarily backend and data infrastructure work during Build, even though early stages touch validate-style scoping. Provisioning Aura, modeling graphs, loading data, and wiring queries maps to backend subphase for graph database products.
Where it fits
Decide graph vs relational fit and capture domain context before provisioning Aura.
Provision Aura, validate the data model MCP, and load seed data for your API.
Wire Neo4j MCP read/write Cypher into the agent loop while building the demo app.
Use explore and query stages to sanity-check graph results before handing off to QA.
How it compares
An orchestrated onboarding pipeline—not a single-purpose Cypher reference or migration checker.
Common Questions / FAQ
Who is neo4j-getting-started-skill for?
Solo builders and coding agents starting a new Neo4j graph project who need staged provisioning, modeling, load, and a minimal runnable artifact.
When should I use neo4j-getting-started-skill?
Use for greenfield Neo4j apps in Build backend, early Validate scoping for graph products, or autonomous ≤15 min demos; defer Cypher-deep dives to neo4j-cypher-skill.
Is neo4j-getting-started-skill safe to install?
It can provision cloud resources and run write Cypher via MCP—review credentials, blast radius, and the Security Audits panel on this page before autonomous runs.
Workflow Chain
Then invoke: neo4j cypher skill
SKILL.md
READMESKILL.md - Neo4j Getting Started Skill
# Neo4j Getting-Started Skill Guide a **user or agent** from zero to a working Neo4j application by executing the 8 stages below in order. **At the start of each stage**: read the corresponding `${CLAUDE_SKILL_DIR}/references/<stage-name>.md` file and follow its instructions. Only load the stage you are currently executing — not all at once. **"User" means both a human developer and an autonomous coding agent.** --- ## When to Use - New Neo4j project from scratch (local/Docker/Aura) - Full onboarding: zero → DB → model → load → app - Generating synthetic data for demos or dev ## When NOT to Use - **Cypher authoring on existing project** → `neo4j-cypher-skill` - **Driver upgrades / Cypher migration** → `neo4j-migration-skill` - **Admin on existing DB** (backup, restore, import) → `neo4j-cli-tools-skill` --- ## Project Structure **All generated code, data, scripts, queries, and notebooks must be written to the working directory** so the user can inspect, reuse, and re-run them after the session ends. Never generate output only as text in the conversation — always write it to a file. Organize files into this layout. Create subdirectories before writing files. ``` .env ← DB credentials (gitignored, loaded by python-dotenv) aura.env ← Aura API credentials (gitignored, never overwrite) progress.md ← stage-by-stage progress (this skill writes it) requirements.txt ← Python dependencies schema/ schema.json ← graph model definition schema.cypher ← DDL: constraints + indexes reset.cypher ← wipe all data (keep schema) data/ generate.py ← synthetic data generator (DATA_SOURCE=synthetic) import.py ← CSV/file importer (DATA_SOURCE=csv or relational) *.csv ← any provided or generated data files queries/ queries.cypher ← validated Cypher query library scripts/ provision_aura.py ← Aura provisioning script (generated during provision stage) notebook.ipynb ← app artifact (root — standard jupyter convention) app.py ← app artifact (root — streamlit run app.py) main.py ← app artifact (root — uvicorn main:app) graphrag_app.py ← app artifact (root) ``` Root-level files (`.env`, `requirements.txt`, app code) stay at root because tooling expects them there. Everything else goes in the appropriate subfolder. --- ## Progress Tracking The skill maintains `progress.md` in the working directory to support resumability. **On startup:** 1. Check if `progress.md` exists. 2. If it exists, find the first pending stage: ```bash grep -B1 "^status: pending" progress.md | grep "^###" | head -1 ``` 3. Resume from that stage. Read its context block (the key=value lines beneath the header) to restore `DOMAIN`, `USE_CASE`, `NEO4J_URI`, etc. — do not re-ask the user for information already recorded. 4.