CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

neo4j-driver-javascript-skill

Neo4j JavaScript/TypeScript Driver v6 — driver lifecycle, executeQuery, managed transactions (executeRead/executeWrite), session.run, Integer handling, JSON serialization, record access, async/await patterns, TypeScript types, error handling, and connection setup for Node.js and browser. Use when writing JS/TS code that connects to Neo4j — neo4j.driver(), executeQuery, executeRead, executeWrite, session.run, neo4j.int, record.get, Integer, BookmarkManager, bolt://, neo4j+s://. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT cover driver version migration — use neo4j-migration-skill.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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, highly actionable reference skill: executable examples throughout, a clear API-selection decision table, and clean progressive disclosure to real, one-level-deep reference files. The only costs are redundant gotcha coverage (Common Mistakes table + Checklist restate inline examples) and missing explicit feedback loops around batch/database operations.

Suggestions

Collapse the 'Common Mistakes' table and final 'Checklist' into a single section — they restate the inline ❌/✅ examples nearly verbatim, and one combined checklist would cut ~40 lines without losing coverage.

Add an explicit post-write verification step to the 'Batch Writes with UNWIND' section (e.g., checking summary.counters.updates().nodesCreated against the input array length) to provide the feedback loop expected for batch database operations.

Show a brief retry/recovery pattern for session.run failures (e.g., catching SERVICE_UNAVAILABLE and re-running once), since it is the one API without auto-retry and currently has no recovery guidance.

DimensionReasoningScore

Conciseness

The body is lean and code-dense with no basic-concept padding, but the 13-row 'Common Mistakes' table and the 13-item 'Checklist' largely restate the inline ❌/✅ guidance, giving a third pass over the same gotchas that could be trimmed. Version-gated notes ('6.3.0+', 'Node 20+') add further tokens, so it sits just below the 'every token earns its place' anchor.

4 / 5

Actionability

Every section ships copy-paste-ready executable code covering the common cases: driver construction with all auth options, all three query APIs, error-code dispatch, TypeScript annotations, and UNWIND batch writes. The '❌/✅' pairs make correct and incorrect usage immediately actionable.

5 / 5

Workflow Clarity

The 'Choose the Right API' decision table sequences API selection, and explicit checkpoints exist (verifyConnectivity() fail-fast, session.close() in finally, error-code handling, counters verification, closing checklist). However, there is no explicit validate→fix→retry feedback loop, and the batch UNWIND section shows no post-write verification step, so it falls short of the top anchor for a database-operations skill.

4 / 5

Progressive Disclosure

The body is a well-organized overview with five one-level-deep references, all of which exist on disk, each introduced with a one-line scope description; 'When NOT to Use' also routes to the RxJS reference. Verified no nested references (only an external GitHub link), so navigation is clean.

5 / 5

Total

18

/

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.

An exemplary description: third-person, dense with concrete capabilities, explicit use-when triggers with API-level keywords and synonyms, and explicit deferral boundaries to sibling skills. No fluff, over-claims, or padding despite its breadth.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities — 'driver lifecycle, executeQuery, managed transactions (executeRead/executeWrite), session.run, Integer handling, JSON serialization, record access, async/await patterns, TypeScript types, error handling, and connection setup' — comprehensively covering the driver domain with no vague language.

5 / 5

Completeness

It explicitly answers both 'what' (the enumerated capability list) and 'when' ('Use when writing JS/TS code that connects to Neo4j') with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Trigger terms are exactly what a developer would say or paste: 'writing JS/TS code that connects to Neo4j', 'neo4j.driver()', 'executeRead', 'session.run', 'neo4j.int', 'record.get', 'bolt://', 'neo4j+s://', with synonyms (JS/TS, JavaScript/TypeScript, Node.js, browser). Only the literal npm package name 'neo4j-driver' is arguably missing, which does not leave a noticeable gap.

5 / 5

Distinctiveness Conflict Risk

Explicit negative boundaries — 'Does NOT handle Cypher query authoring — use neo4j-cypher-skill' and 'Does NOT cover driver version migration — use neo4j-migration-skill' — carve out a clear niche and actively route away sibling skills, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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-javascript-skill/SKILL.md

Reviewed

Table of Contents

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.