neo4j-aura-graph-analytics-skill
Serverless GDS sessions on Neo4j Aura — covers GdsSessions, AuraAPICredentials, DbmsConnectionInfo, SessionMemory, get_or_create, remote graph projection, gds.graph.project.remote, gds.graph.construct, algorithm execution (mutate/stream/write), async job polling, result retrieval, and session lifecycle. Use when running graph algorithms on Aura Business Critical or VDC, processing graph data from Pandas/Spark, or using the graphdatascience Python client in AGA (serverless) mode. Covers all three data source three source modes (AuraDB-connected, self-managed Neo4j, standalone from DataFrames). 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.
79
100%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers specific capabilities, includes rich trigger terms matching natural user language, explicitly states both what the skill does and when to use it, and proactively distinguishes itself from related skills with clear boundary statements. The only minor concern is that the description is quite dense and technical, but given the specialized domain this is appropriate. The 'Does NOT cover' clauses are a best practice that significantly reduces conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists numerous specific concrete actions and concepts: GdsSessions, AuraAPICredentials, remote graph projection, algorithm execution (mutate/stream/write), async job polling, result retrieval, session lifecycle, and specific API methods like gds.graph.project.remote and gds.graph.construct. | 3 / 3 |
Completeness | Clearly answers both 'what' (covers GdsSessions, algorithm execution, session lifecycle, etc.) and 'when' (explicit 'Use when running graph algorithms on Aura Business Critical or VDC, processing graph data from Pandas/Spark, or using the graphdatascience Python client in AGA mode'). Additionally includes explicit negative boundaries with 'Does NOT cover' clauses directing to alternative skills. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would use: 'GdsSessions', 'Aura', 'graph algorithms', 'Pandas', 'Spark', 'graphdatascience Python client', 'AGA', 'serverless', 'Aura Business Critical', 'VDC', 'DataFrames', 'remote graph projection'. These are the exact terms a developer working in this domain would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive — explicitly delineates boundaries with three related skills (neo4j-gds-skill, neo4j-cypher-skill, neo4j-snowflake-graph-analytics-skill) using 'Does NOT cover' clauses, making it very clear when this skill should and should not be selected. The niche of serverless GDS sessions on Neo4j Aura is well-defined. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that covers a complex topic (serverless GDS sessions on Neo4j Aura) with remarkable clarity and efficiency. The content is well-structured with a clear 8-step workflow, three distinct connection modes with executable code for each, a comprehensive error table, and appropriate progressive disclosure to reference files. The 'When to Use' / 'When NOT to Use' sections and deployment decision table provide excellent routing guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It avoids explaining what Neo4j, GDS, or Pandas are, assumes Claude's competence with Python and cloud services, and every section earns its place with concrete code or decision-relevant information. | 3 / 3 |
Actionability | Every step includes fully executable, copy-paste-ready Python code with real imports, environment variable patterns, and concrete API calls. The three connection modes, algorithm execution patterns, and error table all provide specific, actionable guidance. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation checkpoints (verify_connectivity after creation, memory estimation before session creation, async job polling before reading results, write before delete). The checklist at the end reinforces the critical steps, and the common errors table provides a feedback loop for troubleshooting. | 3 / 3 |
Progressive Disclosure | The SKILL.md provides a comprehensive but well-structured overview with clear one-level-deep references to workflows.md and limitations.md for extended content. The WebFetch table and deployment decision table help with navigation. Content is appropriately split between the main file and references. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- neo4j-contrib/neo4j-skills
- Commit
66ed0e1
- 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.