CtrlK
BlogDocsLog inGet started
Tessl Logo

neo4j-aura-graph-analytics-skill

Serverless Aura Graph Analytics (AGA) GDS Sessions — covers GdsSessions, AuraGraphDataScience, AuraAPICredentials, DbmsConnectionInfo, SessionMemory, get_or_create, remote graph projection with gds.v2.graph.project and gds.graph.project.remote, gds.v2 session endpoints, gds.v2.graph.construct, AuraDB Cypher API memory/sessionId projection, algorithms, write-back, and session lifecycle. Use for AuraDB-connected, self-managed Neo4j, or standalone DataFrame/Spark session workloads. Does NOT cover the embedded GDS plugin on Aura Pro or self-managed Neo4j — use neo4j-gds-skill. Does NOT handle Cypher authoring — use neo4j-cypher-skill. Does NOT cover Snowflake Graph Analytics — use neo4j-snowflake-graph-analytics-skill.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 high-quality, dense operational reference with executable code end-to-end, explicit validation and error-recovery loops, and clean deferral of detailed examples to real reference files. The only real weakness is minor redundancy and inline version markers that keep conciseness at 4.

Suggestions

Collapse the 'When NOT to Use' list and the Deployment Decision Table into a single boundary section to remove overlap and tighten conciseness.

Consider moving the graphdatascience-1.22 feature notes (project_native, *_async variants, ML pipelines) into references/limitations.md or a versioning section so the inline body stays version-stable.

Trim the inline 'Session Management' reconnect snippet, which largely repeats Step 3, to reduce token cost.

DimensionReasoningScore

Conciseness

Mostly lean and code-heavy, assuming Claude's knowledge with no concept padding; minor redundancy between the 'When NOT to Use' list and the Deployment Decision Table, plus a few inline version notes, keep it just short of the 'every token earns its place' anchor.

4 / 5

Actionability

Provides fully executable, copy-paste-ready code across all eight steps — auth, estimate, three session-creation modes, four projection methods, mutate/stream/write algorithms, async polling, results, and cleanup — covering the common cases with specific env vars and URLs.

5 / 5

Workflow Clarity

Steps 1–8 are explicitly sequenced with validation checkpoints (verify_session_connectivity, verify_db_connectivity), an async poll-until-RUNNING_DONE loop with error raising, a Common Errors recovery table, and a checklist — feedback loops and validation are present for the batch/database/destructive operations.

5 / 5

Progressive Disclosure

SKILL.md is a navigable overview with full workflow examples and feature tables appropriately split into one-level-deep, clearly signaled references (references/workflows.md, references/limitations.md), both of which exist as real files.

5 / 5

Total

19

/

20

Passed

Description

87%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.

A strong, third-person description with clear what/when coverage and excellent sibling-skill boundary guidance. Slightly leans on internal class-name enumeration rather than user-facing action language, which keeps specificity and trigger coverage at 4 rather than 5.

DimensionReasoningScore

Specificity

Lists many concrete capabilities — get_or_create, remote projection with gds.v2.graph.project/gds.graph.project.remote, gds.v2.graph.construct, algorithms, write-back, session lifecycle — fitting 'lists several specific actions'. Falls short of 5 because it leans on enumerating internal class names rather than a fully comprehensive set of user-facing actions.

4 / 5

Completeness

Explicitly answers what (covers GDS Sessions, projection, algorithms, write-back, lifecycle) and when ('Use for AuraDB-connected, self-managed Neo4j, or standalone DataFrame/Spark session workloads') with concrete trigger phrases, matching the 'clearly and explicitly answers both' anchor.

5 / 5

Trigger Term Quality

Includes natural domain vocabulary a user would say — 'GDS algorithms', 'AuraDB', 'self-managed Neo4j', 'DataFrame/Spark', 'graph projection', 'Cypher API' — giving good keyword coverage. Not a 5 because some natural synonyms (e.g. 'graph data science' spelled out) are absent.

4 / 5

Distinctiveness Conflict Risk

Has explicit boundary disambiguation ('Does NOT cover... use neo4j-gds-skill', 'Does NOT handle Cypher authoring — use neo4j-cypher-skill', 'Does NOT cover Snowflake...') giving a clear serverless-AGA niche with minimal conflict risk.

5 / 5

Total

18

/

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.