Neo4j Gds Skill

# neo4j-gds-skill

Agent skill for Neo4j Graph Data Science (GDS) embedded plugin through the Python client or Cypher. Use for Aura Pro, self-managed, local, or offline Neo4j DBMS with the GDS plugin installed.

## What this skill covers

- Graph projection: native projection and Cypher projection
- Execution modes: stream / stats / mutate / write and when to use each
- Core algorithms: PageRank, Louvain, WCC, Betweenness Centrality, Node Similarity, FastRP, KNN
- FastRP → KNN recommendation pipeline pattern
- Writing node embeddings for Neo4j vector indexes / structural similarity search
- Memory estimation before large projections and algorithm runs
- GDS Python client (`graphdatascience`) — v2 connection, projection, algorithm calls; v1 fallback when needed
- Graph catalog operations: project, list, drop, subgraph filter
- Common errors and mitigations (OOM, missing properties, unlicensed algorithms)

## Compatibility

- GDS Python client v1.21: GDS >= 2.6 and < 2.28 / < 2026.4
- Embedded GDS plugin: Neo4j >= 5.x self-managed/local or Aura Pro plugin workflows
- Python >= 3.10 and < 3.15
- Neo4j Python Driver >= 4.4.12 and < 7.0

## Not covered

- **Cypher query authoring** → `neo4j-cypher-skill`
- **Driver/connection setup** → `neo4j-driver-python-skill`
- **Creating/querying vector indexes over written embeddings** → `neo4j-vector-index-skill`
- **Aura Graph Analytics Sessions / AGA** → `neo4j-aura-graph-analytics-skill`

## Install

```bash
pip install graphdatascience
```

```bash
npx skills add https://github.com/neo4j-contrib/neo4j-skills --skill neo4j-gds-skill
```


# GDS Algorithm Reference

Core catalog of commonly used GDS procedures. Mode availability varies by algorithm; check `CALL gds.list()` or the algorithm syntax page before assuming `stream` / `stats` / `mutate` / `write`.

Python client: prefer `gds.v2.*` endpoints and snake_case parameters. Procedure tables show Cypher procedure names.

## Centrality

| Algorithm | Procedure | Best For |
|---|---|---|
| PageRank | `gds.pageRank` | Network influence via incoming links |
| Betweenness Centrality | `gds.betweenness` | Bottleneck/bridge nodes |
| Degree Centrality | `gds.degree` | Most-connected nodes (fast) |
| ArticleRank | `gds.articleRank` | PageRank variant dampening high-degree nodes |
| Eigenvector | `gds.eigenvector` | Influence via well-connected neighbors |
| Closeness | `gds.closeness` | Average distance to all other nodes |
| HITS | `gds.hits` | Authority/hub scores (web-like graphs) |

### PageRank — key parameters
| V2 parameter | Cypher/v1 parameter | Default | Notes |
|---|---|---|---|
| `damping_factor` | `dampingFactor` | 0.85 | Probability of following a link; lower = more teleportation |
| `max_iterations` | `maxIterations` | 20 | |
| `tolerance` | `tolerance` | 1e-7 | Convergence threshold |
| `relationship_weight_property` | `relationshipWeightProperty` | — | Optional weight property |

Spider traps (closed groups, no outlinks) inflate scores — increase `dampingFactor`. Negative weights silently ignored.

---

## Community Detection

| Algorithm | Procedure | Notes |
|---|---|---|
| Louvain | `gds.louvain` | Best general-purpose; modularity maximization |
| Leiden | `gds.leiden` | Refinement of Louvain; avoids poorly connected communities |
| WCC | `gds.wcc` | Weakly connected components; run first to partition graph |
| SCC | `gds.scc` | Strongly connected components (directed graphs only) |
| Label Propagation | `gds.labelPropagation` | Fast, large graphs; non-deterministic |
| K-Core Decomposition | `gds.kcore` | Dense subgraphs by degree threshold |
| Triangle Count | `gds.triangleCount` | Counts triangles per node; prerequisite for LCC |
| Local Clustering Coefficient | `gds.localClusteringCoefficient` | Ratio of closed triangles |
| K-Means | `gds.kmeans` | Requires node embedding properties as input |
| HDBSCAN | `gds.hdbscan` | Density-based; finds variable-density communities |

### WCC parameters
| Parameter | Notes |
|---|--