neo4j-driver-python-skill

Neo4j Python Driver v6 — driver lifecycle, execute_query, managed and explicit transactions, async (AsyncGraphDatabase), result handling, data type mapping, error handling, UNWIND batching, connection pool tuning, and causal consistency. Use when writing Python code that connects to Neo4j via GraphDatabase.driver, execute_query, execute_read, execute_write, AsyncGraphDatabase, neo4j.Result, or RoutingControl. Package name is `neo4j` (not neo4j-driver) since v6. Python >=3.10 required. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT cover driver upgrades or breaking changes — use neo4j-migration-skill. Does NOT cover GraphRAG pipelines (neo4j-graphrag package) — use neo4j-graphrag-skill.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%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 dense, executable reference with excellent actionability and clean progressive disclosure via real reference files. Its main weakness is workflow clarity for batch/destructive writes, where an explicit validation/feedback loop is missing, capping that dimension.

Suggestions

Add an explicit validate→fix→retry feedback loop for batch/destructive writes (e.g., after UNWIND/execute_write, verify counts via summary.counters and retry on transient ConstraintError) so workflow_clarity is not capped at 3.

Consolidate the scattered version-gate markers ([6.2+], [6.3+], etc.) into a single 'Version compatibility' or 'Deprecated/old patterns' section to tighten conciseness and keep the main body evergreen.

Consider a short numbered 'write path' checklist (parameterize → set database_ → execute → verify counters → handle ConstraintError first) to make the destructive workflow explicit alongside the existing end-of-file checklist.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence with no introductory padding, but time-sensitive version markers ([6.2+], [6.3+]) are inlined throughout rather than consolidated in a deprecated/old-patterns section, which the guidelines treat as a minor conciseness cost.	4 / 5
Actionability	Copy-paste-ready executable code spans every major path (driver setup, execute_query, managed transactions, async, error handling, UNWIND batching, pool tuning) plus comparison tables, fully covering the common cases.	5 / 5
Workflow Clarity	API selection is clearly sequenced via the 'Choosing the Right API' table and a checklist provides checkpoints, but destructive/batch writes (UNWIND, execute_write) lack an explicit validate→fix→retry feedback loop, which caps workflow clarity at 3 per the database/batch-operations rule.	3 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled, one-level-deep references to references/async.md, data-types.md, performance.md, and transactions.md (all real files), each pointed to inline and again in a dedicated References section — content is appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

92%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 that names many concrete capabilities and pairs them with explicit trigger terms and clear negative-boundary guidance. It is dense but not padded, and the only minor gap is a few natural-synonym triggers.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete capabilities — 'driver lifecycle, execute_query, managed and explicit transactions, async (AsyncGraphDatabase), result handling, data type mapping, error handling, UNWIND batching, connection pool tuning, and causal consistency' — comprehensive coverage of specific actions rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated capability list) and 'when' ('Use when writing Python code that connects to Neo4j via ...'), with concrete trigger phrases — matching the anchor that clearly answers both with concrete triggers.	5 / 5
Trigger Term Quality	'Use when writing Python code that connects to Neo4j via GraphDatabase.driver, execute_query, execute_read, execute_write, AsyncGraphDatabase, neo4j.Result, or RoutingControl' surfaces the natural API symbols a developer would reference; good coverage with a few common phrasings or synonyms absent, so just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Neo4j Python Driver v6) reinforced by explicit 'Does NOT' boundary clauses redirecting Cypher, migration, and GraphRAG work to sibling skills, giving minimal conflict risk.	5 / 5
	Total	19 / 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-driver-python-skill/SKILL.md
Commit: a3627d2

Reviewed: 4 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.