neo4j-aura-provisioning-skill

Provisions and manages Neo4j Aura instances via CLI (aura-cli v1.7+) or REST API. Use when creating, pausing, resuming, resizing, or deleting AuraDB Free/Professional/Business Critical/VDC instances; downloading credentials; scripting CI/CD pipelines; polling async status; or using the Terraform neo4j/neo4j-aura provider. Covers auth setup (client credentials OAuth2), credential lifecycle (download once — never recoverable), instance type selection, region codes, and Python provisioning scripts. Does NOT handle Cypher queries — use neo4j-cypher-skill. Does NOT cover Graph Data Science algorithms — use neo4j-gds-skill or neo4j-aura-graph-analytics-skill. Does NOT cover neo4j-admin/cypher-shell — use neo4j-cli-tools-skill.

1.78x

Quality

92%

Does it follow best practices?

Impact

100%

1.78x

Average score across 1 eval scenario

Securityby

High

Do not use without reviewing

Quality

Content

85%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, actionable, well-sequenced provisioning workflow with excellent validation and error-recovery structure. Its main weakness is progressive disclosure: existing reference files are unmentioned and bulk reference content is inlined rather than split out.

Suggestions

Add clearly signaled one-level-deep links to the existing reference files (e.g., "Tier comparison details: see [aura-tiers.md](references/aura-tiers.md)"; "Monitoring/metrics: see [aura-monitoring.md](references/aura-monitoring.md)"), and surface aura-agent.md and data-importer.md where relevant.

Move the full per-provider region tables and the complete Python CI/CD / Terraform blocks into references/ (e.g., references/regions.md, references/python-provisioning.md), keeping only a representative example inline in SKILL.md.

Tighten the inlined tier decision table by deferring the AuraDS rows and full memory ranges to aura-tiers.md, retaining only the Free/Professional/Business Critical/VDC rows needed for the primary provisioning decision.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense with minimal concept re-explanation, but it inlines bulk reference material that could be offloaded — full AWS/GCP/Azure region tables (~40 lines), a complete Python CI/CD script, and a full Terraform provider block — rather than assuming Claude can look those up. Falls below the 5 anchor ("every token earns its place") but well above the 3 anchor.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance across all surfaces: aura-cli commands, REST curl calls with auth headers, a complete Python provisioning script, and Terraform HCL, covering the common cases with specific field tables.	5 / 5
Workflow Clarity	Steps 1–5 are clearly sequenced with explicit validation checkpoints (poll_status until running/paused), a status lifecycle diagram, per-operation required-state guards, an error-recovery table, and a final checklist that confirms destructive delete ops with the user.	5 / 5
Progressive Disclosure	Four real bundle files exist in references/ (aura-agent, aura-monitoring, aura-tiers, data-importer) but the body never links to or signals them, while large reference-style content (region tables, full scripts, tier table) is inlined in SKILL.md — matching the 3 anchor where "references present but not clearly signaled; content that should be separate is inline."	3 / 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.

The description is exemplary: concrete actions, explicit trigger guidance, both what-and-when, and strong boundary statements naming sibling skills. It is on the longer side but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "creating, pausing, resuming, resizing, or deleting," "downloading credentials," "scripting CI/CD pipelines," "polling async status," "Terraform provider" — plus explicit out-of-scope boundaries, giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both "what" ("Provisions and manages Neo4j Aura instances via CLI... or REST API") and "when" ("Use when creating, pausing, resuming, resizing, or deleting...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ("create Aura instance," "pause/resume/resize/delete," "download credentials," "CI/CD pipelines") alongside tier names (Free/Professional/Business Critical/VDC) and tool identifiers (aura-cli, neo4j/neo4j-aura), covering the vocabulary a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Three explicit "Does NOT... use <sibling-skill>" boundary clauses (Cypher, GDS, neo4j-admin/cypher-shell) carve a clear niche with minimal risk of triggering for the wrong skill.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: neo4j-contrib/neo4j-skills
Path: neo4j-aura-provisioning-skill/SKILL.md
Commit: a9a5e78

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.