neo4j-aura-agent-skill

Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, or invoking agents with natural language queries. Covers OAuth2 auth, organization/project scoping, tool parameter schemas, and InvokeAgentResponse format. Does NOT cover AuraDB instance provisioning — use neo4j-aura-provisioning-skill. Does NOT cover vector index creation — use neo4j-vector-index-skill.

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

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 is specific, comprehensive, and well-bounded. It lists concrete actions, includes rich trigger terms relevant to the Neo4j Aura ecosystem, explicitly states both what it does and when to use it, and proactively distinguishes itself from related skills with clear negative boundaries. The third-person voice is used correctly throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: create, list, get, update, delete, and invoke Aura agents. Also specifies concrete tool types (CypherTemplate, SimilaritySearch, Text2Cypher), system prompts, deploying to REST/MCP endpoints, and invoking with natural language queries.	3 / 3
Completeness	Clearly answers both 'what' (manages Neo4j Aura Agents via CRUD operations and invocation) and 'when' ('Use when configuring Aura Agent tools, setting system prompts, deploying agents, or invoking agents'). Also includes explicit negative boundaries directing to other skills, which strengthens the 'when' guidance.	3 / 3
Trigger Term Quality	Excellent coverage of natural keywords: 'Neo4j', 'Aura Agents', 'REST API', 'CypherTemplate', 'SimilaritySearch', 'Text2Cypher', 'system prompts', 'MCP endpoints', 'OAuth2', 'AuraDB', 'InvokeAgentResponse'. These are terms a user working with Neo4j Aura Agents would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche (Neo4j Aura Agents v2beta1 API). Explicitly delineates boundaries by stating what it does NOT cover and pointing to specific alternative skills (neo4j-aura-provisioning-skill, neo4j-vector-index-skill), minimizing conflict risk.	3 / 3
	Total	12 / 12 Passed

Implementation

85%

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

This is a strong, well-structured skill that provides a clear end-to-end workflow for managing Neo4j Aura Agents with excellent validation checkpoints and user confirmation gates. The actionability is outstanding with executable commands, complete JSON schemas, and specific error remediation. The main weakness is moderate verbosity — some sections could be consolidated (e.g., tool configuration appears in both Step 5 and the dedicated Tool Configuration section), and repetitive 'Stop and report' patterns add token overhead.

Suggestions

Consolidate the Tool Configuration reference section with Step 5's tool selection guidance to reduce duplication — consider moving the full JSON schemas to a reference file and keeping only a brief summary inline.

Dimension	Reasoning	Score
Conciseness	The skill is generally efficient and avoids explaining basic concepts, but it's quite long (~300+ lines) with some sections that could be tightened — e.g., the detailed parameter tables for each script, the 'What are Aura Agents' section explaining tool types Claude could infer, and some repetitive error-handling instructions ('Stop and report' appears many times). The tool configuration section partially duplicates what's already shown in Step 5.	2 / 3
Actionability	Highly actionable throughout — provides executable bash commands, complete JSON config examples with field-level guidance, specific script invocations with platform variants (Linux/macOS vs Windows), and concrete instructions for resolving each parameter from schema.json. The CypherTemplate, SimilaritySearch, and Text2Cypher configs are copy-paste ready with clear field explanations.	3 / 3
Workflow Clarity	Excellent sequential workflow (Steps 1-9) with explicit validation checkpoints at every step — auth verification, data gate in Step 4 (≥2 nodes, ≥1 rel type), user confirmation gates before create/update/delete, error-specific remediation instructions, and a comprehensive checklist at the end. Feedback loops are present (401 → re-run Step 1, validation fail → stop and report).	3 / 3
Progressive Disclosure	The SKILL.md serves as a clear operational overview with well-signaled one-level-deep references to `references/authoring-guide.md` and `references/REFERENCE.md` for detailed content (embedding provider options, signals inventory template). Scripts are referenced by path with parameter tables. Content is appropriately split between the main file and supporting references.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 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: about 23 hours 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.