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.

1.92x

Quality

86%

Does it follow best practices?

Impact

100%

1.92x

Average score across 3 eval scenarios

Securityby

Medium

Suggest reviewing before use

Quality

Content

73%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 highly actionable, well-sequenced provisioning guide with strong validation checkpoints, weakened mainly by inlined reference-grade content and a bundle of reference files that the body never points to.

Suggestions

Add a '## References' section linking the existing bundle files (aura-tiers.md, data-importer.md, aura-monitoring.md, aura-agent.md) and move the duplicated tier/connection and region-code tables into those files, keeping only a compact quick-reference inline.

Move the full Python CI/CD script and Terraform block into reference files (or a scripts/ entry) and reference them by path to reduce body length, since the core flow is already demonstrated by the CLI/REST snippets.

Tighten the Common Errors and API Rate Limits tables by folding rate-limit guidance into the poll_status section so the two are not maintained in separate places.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no beginner padding), but inlines reference-grade material — three full region-code tables (~40 rows), a full Python script, a full Terraform block — much of which duplicates references/aura-tiers.md and could be trimmed or moved.	3 / 5
Actionability	Copy-paste-ready curl/aura-cli commands with real flags, a working Python provisioning script, Terraform HCL, and a reusable poll_status shell function cover the common create/poll/lifecycle cases fully.	5 / 5
Workflow Clarity	Explicit Step 1–5 sequence with CRITICAL async-poll warnings, required-state preconditions for each lifecycle op, a poll_status helper, a Common Errors table, and a final Checklist provide explicit validation checkpoints and feedback loops around destructive/async operations.	5 / 5
Progressive Disclosure	Four bundle files exist (references/aura-agent.md, aura-monitoring.md, aura-tiers.md, data-importer.md) but the body never links to any of them, and tier/connection content that belongs in those files is inlined instead — references are present yet entirely unsignaled.	2 / 5
	Total	15 / 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.

A strong, specific description with concrete actions, natural triggers, and explicit when-guidance, reinforced by clear boundary routing to sibling skills. It avoids vagueness and over-claims entirely.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating, pausing, resuming, resizing, or deleting', 'downloading credentials', 'scripting CI/CD pipelines', 'polling async status' — bound to specific tools (aura-cli v1.7+, REST API, Terraform neo4j/neo4j-aura), giving comprehensive concrete coverage.	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	Natural trigger phrases ('creating, pausing, resuming, resizing, or deleting AuraDB instances', 'scripting CI/CD pipelines', 'downloading credentials', 'polling async status') plus tier names and tool identifiers cover the terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Three explicit 'Does NOT ... use <sibling-skill>' clauses route Cypher, GDS, and neo4j-admin/cypher-shell away, carving a clear niche with minimal conflict risk.	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: 02ad354

Reviewed: 3 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.