neo4j-driver-dotnet-skill

Neo4j .NET Driver v6 — IDriver lifecycle, DI registration (singleton), ExecutableQuery fluent API, ExecuteReadAsync/ExecuteWriteAsync managed transactions, IResultCursor (FetchAsync/ ToListAsync), record value access (.Get<T>/As<T>), null safety, UNWIND batching, temporal types, await using, EagerResult, object mapping, CancellationToken, error handling, and common traps. Use when writing C# or .NET code connecting to Neo4j. Also triggers on Neo4j.Driver, IDriver, ExecutableQuery, ExecuteReadAsync, ExecuteWriteAsync, IResultCursor, IAsyncSession, or any Bolt/Aura work in .NET/C#. Does NOT handle Cypher authoring — use neo4j-cypher-skill. Does NOT cover driver version upgrades — use neo4j-migration-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 highly actionable, well-structured reference skill with copy-paste code and clean progressive disclosure into real bundle files. The main gap is the absence of an explicit validate-fix-retry feedback loop for database/batch operations, which caps workflow clarity.

Suggestions

Add an explicit validate -> fix -> retry feedback loop for write/batch operations (e.g., verify Connectivity/bookmarks or catch-and-retry on transient errors) so the database workflow meets the validation-checkpoint bar.

Trim the Common Mistakes table entries that duplicate the inline wrong/right code blocks, or consolidate one of the two to reduce repetition and save tokens.

Tighten editorial prose asides (e.g., '**use this**', 'fail fast on startup') into the surrounding technical statements to lift conciseness toward the lean anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense and skill-specific with no padding about what Neo4j/C#/DI are, but a few prose asides and a sprawling Common Mistakes table that partly duplicates the inline wrong/right blocks could be trimmed, keeping it just below the lean anchor.	4 / 5
Actionability	Provides extensive copy-paste-ready C# covering ExecutableQuery, managed transactions, FetchAsync loops, record access, type mapping, UNWIND batching, object mapping, and error handling, plus install and DI registration commands across the common cases.	5 / 5
Workflow Clarity	Sequencing is present via the 'Choose the Right API' decision table and a closing Checklist, but for a database/batch skill the rubric expects an explicit validate-fix-retry feedback loop, which is absent (the Checklist is a static lint list), capping this dimension at 3.	3 / 5
Progressive Disclosure	The body is a clear overview that signals three one-level-deep reference files (transactions.md, performance.md, object-mapping.md), all verified to exist, with explicit per-file navigation ('Load on demand:') while keeping core patterns inline.	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 clearly answers what the skill does and when to use it, with concrete API triggers and explicit boundaries against sibling skills. The only soft spot is trigger phrasing that favors technical type names over natural user synonyms.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions and APIs (IDriver lifecycle, DI singleton registration, ExecutableQuery fluent API, ExecuteReadAsync/ExecuteWriteAsync, IResultCursor FetchAsync/ToListAsync, .Get<T>/As<T>, null safety, UNWIND batching, temporal types, await using, EagerResult, object mapping, CancellationToken, error handling), giving comprehensive coverage rather than just a few.	5 / 5
Completeness	Explicitly states both what the skill does (the long capability list) and when to use it ('Use when writing C# or .NET code connecting to Neo4j... Also triggers on...'), plus explicit when-not-to exclusions, matching the anchor that requires concrete answers to both what and when.	5 / 5
Trigger Term Quality	Good keyword coverage including the API type names (Neo4j.Driver, IDriver, ExecutableQuery, IAsyncSession) and Bolt/Aura plus 'C# or .NET code connecting to Neo4j', but it leans on technical type names over natural user phrasings and is missing a few common synonyms, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Explicitly disambiguates from sibling skills ('Does NOT handle Cypher authoring — use neo4j-cypher-skill', 'Does NOT cover driver version upgrades — use neo4j-migration-skill') and occupies a distinct .NET/C# driver-v6 niche with type-name triggers, 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-dotnet-skill/SKILL.md
Commit: a9a5e78

Reviewed: 6 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.