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, exact SQL CALL syntax, and privilege setup in both modes — app-identity grants and execute-as-user / per-user PAT auth (programmatic access token, set_enable_custom_credentials, register_user_role, caller grants). 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.
94
94%
Does it follow best practices?
Impact
94%
1.70xAverage score across 3 eval scenarios
High
Do not use without reviewing
Evaluation results
100%
50%Customer Network Analysis: Grouping Customers by Transaction Patterns
Louvain community detection view and CALL generation
Node view name
0%
100%
Relationship view name
0%
100%
NODEID key column
0%
100%
SOURCENODEID and TARGETNODEID
0%
100%
Explicit property CASTs
28%
100%
Unsupported types dropped
100%
100%
Dropped columns explained
62%
100%
Fractional numerics to DOUBLE
0%
100%
Whole-number numerics to BIGINT
0%
100%
UNDIRECTED orientation
100%
100%
CPU_X64_XS compute pool
100%
100%
Output table naming
0%
100%
Write is a list
100%
100%
Single-quoted JSON
100%
100%
Result join on NODEID
100%
100%
100%
24%Influencer Discovery with Neo4j Graph Analytics in Snowflake
PageRank on social follow graph with privilege setup
Part A consumer privileges
100%
100%
App-identity mode chosen
100%
100%
App role grants
100%
100%
Source data exploration
100%
100%
Projection views created
100%
100%
Explicit CASTs on properties
0%
100%
Key column naming and casting
42%
100%
Node view naming
0%
100%
Relationship view naming
0%
100%
NATURAL orientation
100%
100%
Single-quoted JSON config
100%
100%
defaultTablePrefix set
100%
100%
Write config is a list
100%
100%
CPU_X64_XS compute pool
100%
100%
Output table naming
0%
100%
Join back to USERS
100%
100%
No null config parameters
100%
100%
82%
43%Product Similarity Recommendations with Snowflake Graph Analytics
FastRP→KNN product similarity with mixed-type projection views
Node view suffix
0%
100%
Relationship view suffix
0%
100%
NODEID cast to BIGINT
0%
100%
SOURCENODEID and TARGETNODEID
28%
100%
Explicit CASTs on all properties
0%
100%
ARRAY columns in node view
100%
0%
No ARRAY in relationship view
100%
100%
FLOAT columns cast to DOUBLE
0%
100%
Dropped columns documented
0%
100%
FastRP chained into KNN
0%
0%
Result table naming
0%
100%
CPU_X64_XS compute pool
100%
100%
JSON single quotes in CALL
100%
100%
write config is a list
100%
100%
Double join for product names
100%
100%
- Repository
- neo4j-contrib/neo4j-skills
- Commit
a3627d2
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
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.