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

90%

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 high-quality, action-dense driver reference with excellent progressive disclosure and copy-paste code throughout. Its one weak spot is workflow clarity on batch/destructive write paths, which present idempotency notes and counters but no explicit post-batch validation loop.

Suggestions

Add an explicit validate-after-batch step to the UNWIND section (e.g., compare summary.counters.nodes_created to len(rows) or re-query a sample) so destructive/batch workflows have a checkpoint, lifting workflow_clarity above the cap.

Tighten conciseness by collapsing the standalone dotenv Environment Variables section into a brief pointer or folding it into Driver Lifecycle, and de-duplicate the database_ round-trip note (stated in both Performance and Common Errors).

Consolidate the scattered [6.1+]/[6.2+] version markers into a single version-compatibility note (or a small 'Deprecated since v6' section) to reduce inline time-sensitive clutter.

Dimension	Reasoning	Score
Conciseness	Dense reference-style body with tables, terse bullets, and no beginner-concept padding, but the dotenv environment-variable section and a few restated points (database_ round-trip appears twice) plus inline version markers [6.1+]/[6.2+] keep it just short of lean-and-efficient.	4 / 5
Actionability	Copy-paste-ready code for every core API (driver lifecycle, execute_query, managed tx, async + FastAPI lifespan + gather, error handling, UNWIND batch, pool tuning) plus a mistake→fix Common Errors table and a checklist — fully executable covering common cases.	5 / 5
Workflow Clarity	Multi-step processes carry checkpoints (verify_connectivity, .consume(), exception ordering) and a checklist, but the UNWIND batch and execute_write write paths lack an explicit validate-after-batch verification step, so the destructive/batch cap applies and holds it at 3.	3 / 5
Progressive Disclosure	Clear sections each signal a one-level-deep reference (async.md, data-types.md, performance.md, transactions.md); all four referenced files exist in ./references/ with no nested references, matching the clear-overview anchor exactly.	5 / 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: it states comprehensive concrete capabilities, gives explicit symbol-level trigger terms for when to use it, and delineates three adjacent skills via negative boundaries. It is third-person, concise for its breadth, and free of fluff.

Dimension	Reasoning	Score
Specificity	Enumerates 10+ concrete capabilities — driver lifecycle, execute_query, managed/explicit transactions, async, result handling, data type mapping, error handling, UNWIND batching, pool tuning, causal consistency — matching the comprehensive-coverage anchor; a couple of items are domains rather than crisp verbs but it sits closer to 5 than 4.	5 / 5
Completeness	Explicitly answers both what (the enumerated capabilities) and when ('Use when writing Python code that connects to Neo4j via …') with concrete trigger phrases, and adds negative boundaries — matching the anchor exactly.	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' covers the actual symbol names a developer would type, plus synonyms (neo4j package, AsyncGraphDatabase), matching comprehensive coverage.	5 / 5
Distinctiveness Conflict Risk	Explicit 'Does NOT handle Cypher … use neo4j-cypher-skill', 'Does NOT cover driver upgrades … use neo4j-migration-skill', and 'Does NOT cover GraphRAG … use neo4j-graphrag-skill' carve 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-driver-python-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.