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 installation, privilege setup, project-compute-write pattern, and 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.

1.36x

Quality

82%

Does it follow best practices?

Impact

100%

1.36x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

21%

Snowflake Graph Analytics Environment Setup

Privilege setup SQL script generation

Criteria

Without context

With context

USE ACCOUNTADMIN

100%

Consumer role creation

100%

app_user grant to consumer role

100%

Current user grant

100%

Database role creation

100%

SELECT grants to database role

62%

100%

FUTURE TABLES grant to database role

100%

CREATE TABLE grant to database role

100%

Database role granted to app

100%

Consumer role FUTURE TABLES

100%

Correct app name

66%

100%

Switch to consumer role

100%

Customer Community Segmentation with Graph Analytics

View aliasing and Louvain community detection

Criteria

Without context

With context

Node view with nodeId alias

100%

Relationship view with sourceNodeId/targetNodeId

100%

Categorical to numeric conversion

100%

CALL Louvain syntax

100%

project section present

100%

Views referenced in projection

100%

UNDIRECTED orientation

100%

write section present

100%

nodeLabel without schema prefix

100%

compute section present

100%

Correct compute pool

100%

58%

Content Similarity Recommendations via Graph Embeddings

Chained FastRP and KNN for content recommendations

Criteria

Without context

With context

FastRP CALL statement

40%

100%

KNN CALL statement

20%

100%

FastRP before KNN

100%

FastRP output table referenced in KNN

50%

100%

KNN write uses relationshipType

100%

KNN outputTable targets SHOW_SIMILARITIES

50%

100%

UNDIRECTED orientation

30%

100%

Non-XS compute pool

100%

project section in both CALLs

100%

write section in both CALLs

100%

View or column aliasing

100%

Repository: neo4j-contrib/neo4j-skills
Commit: 66ed0e1

Evaluated: about 23 hours ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Snowflake Graph Analytics Environment Setup Customer Community Segmentation with Graph Analytics Content Similarity Recommendations via Graph Embeddings

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.