CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

93

1.65x
Quality

91%

Does it follow best practices?

Impact

99%

1.65x

Average score across 3 eval scenarios

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, highly actionable skill body with executable SQL throughout and a sensible four-step workflow supported by a checklist and troubleshooting table. Minor room to tighten the intro and add an explicit post-CALL validation checkpoint before joining results.

Suggestions

Trim the opening tagline ('Snowflake Native App — graph algorithm power inside Snowflake...') since it restates the description and the 'When to Use' section.

Add an explicit inline checkpoint after the CALL in Step 3 (e.g. 'Verify the output table is populated and non-empty before joining') to strengthen the validation feedback loop for these batch write operations.

Consider moving the lengthy Privilege Setup SQL block to a references file linked from the main body to keep the core analytics flow tighter.

DimensionReasoningScore

Conciseness

The body is largely lean and domain-specific (strict casting rules, exact CALL syntax) without explaining concepts Claude already knows, but the opening tagline and slight overlap between the intro and 'When to Use' could be trimmed, sitting at anchor 4 rather than 5.

4 / 5

Actionability

Fully executable, copy-paste-ready SQL: complete CREATE VIEW statements with explicit casts, a complete CALL with project/compute/write config, and a full privilege-setup block — concrete examples cover the common cases per anchor 5.

5 / 5

Workflow Clarity

Clear numbered sequence (Explore → Prepare views → Project-Compute-Write → Inspect) with a closing checklist and a Troubleshooting table for error recovery, but the main flow lacks an explicit inline 'verify output populated before joining' checkpoint, so it sits at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Good structure with a well-signaled one-level-deep reference to references/algorithms.md (verified to exist) for the full parameter reference, but several large inline sections (privilege setup SQL, full algorithm tables) keep it just below the cleanly-split anchor 5.

4 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: third-person voice, concrete actions, explicit 'Use when' trigger with multiple synonyms, and clear boundary clauses steering away from three sibling skills. Every dimension lands at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data' plus the 'explore → prepare projection views → project-compute-write flow' — matching the comprehensive-coverage anchor 5.

5 / 5

Completeness

Explicitly answers both what ('Run Neo4j Graph Analytics algorithms ... directly inside Snowflake') and when ('Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App') with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

Includes natural trigger phrases and synonyms users would say — 'graph algorithms in Snowflake', 'GDS Snowflake', 'Neo4j Graph Analytics', 'Neo4j Snowflake Native App' — comprehensively covering the ways a user would name this need.

5 / 5

Distinctiveness Conflict Risk

Clear niche with three explicit deconfliction clauses ('Does NOT cover Cypher ... use neo4j-cypher-skill', 'Does NOT cover Aura Graph Analytics', 'Does NOT cover self-managed GDS'), giving minimal conflict risk per anchor 5.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
neo4j-contrib/neo4j-skills
Reviewed

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.