neo4j-snowflake-graph-analytics-skill

Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data. Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App ("GDS Snowflake", "graph algorithms in Snowflake", "Neo4j Graph Analytics"). Covers the explore → prepare projection views → project-compute-write flow, the strict view/column type rules the graph engine requires, and exact SQL CALL syntax. Does NOT cover Cypher or Neo4j DBMS queries — use neo4j-cypher-skill. Does NOT cover Aura Graph Analytics — use neo4j-aura-graph-analytics-skill. Does NOT cover self-managed GDS — use neo4j-gds-skill.

1.65x

Quality

88%

Does it follow best practices?

Impact

99%

1.65x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

100%

82%

Product Co-Purchase Graph: Projection Views

Projection view creation with correct casting

Criteria

Without context

With context

Node view naming

100%

Relationship view naming

100%

NODEID explicit cast

100%

SOURCENODEID and TARGETNODEID casts

100%

Integer columns cast to BIGINT

100%

Decimal columns cast to DOUBLE

87%

100%

VARCHAR columns dropped from node view

100%

BOOLEAN column dropped or converted

100%

TIMESTAMP column dropped or converted

100%

No ARRAY/VECTOR in relationship view

100%

Date column dropped from relationship view

100%

Dropped columns documented

50%

100%

21%

Identifying Influential Research Articles via Citation Analysis

End-to-end PageRank workflow with result lookup

Criteria

Without context

With context

Uses PageRank algorithm

100%

Node view with NODEID cast

50%

100%

Relationship view with SOURCENODEID/TARGETNODEID

50%

100%

NATURAL orientation for PageRank

50%

100%

CALL uses single-quotes JSON

100%

Config has project/compute/write sections

100%

write is a list

100%

Output table naming convention

100%

defaultTablePrefix set

100%

Result joined to source table

100%

VARCHAR columns dropped from node view

100%

CPU_X64_XS compute pool

100%

97%

13%

Customer Segmentation via Graph Embeddings and Similarity

Algorithm chaining with privilege setup (FastRP → KNN)

Criteria

Without context

With context

FUTURE TABLE grant included

100%

FUTURE VIEW grant included

100%

CREATE TABLE grant included

100%

VARCHAR columns dropped from node view

100%

DATE column handled

100%

FastRP embedding CALL

100%

KNN CALL after embeddings

100%

Chained output used as input

100%

Output table naming convention

62%

NODEID explicit cast in node view

100%

write config is a list

100%

defaultTablePrefix in both CALLs

100%

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

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

Table of Contents

Product Co-Purchase Graph: Projection Views Identifying Influential Research Articles via Citation Analysis Customer Segmentation via Graph Embeddings and Similarity

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.