CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

neo4j-graphql-skill

Build and configure a GraphQL API backed by Neo4j using @neo4j/graphql v7 (current) or v5 (LTS). Covers Neo4jGraphQL constructor, getSchema(), assertIndexesAndConstraints(), type definitions with @node, @relationship (IN/OUT/UNDIRECTED), @cypher for custom resolvers, @authorization/@authentication for JWT/JWKS security, auto-generated queries/mutations, OGM programmatic access, subscriptions via CDC, and Apollo Federation. Use when writing typeDefs, securing fields, or wiring Neo4j to Apollo Server. Does NOT handle raw Cypher outside resolvers — use neo4j-cypher-skill. Does NOT cover Spring Data Neo4j entity mapping — use neo4j-spring-data-skill.

88

1.10x
Quality

87%

Does it follow best practices?

Impact

94%

1.10x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 body: executable code everywhere, version-specific gotchas, a breaking-changes section, an error table, and a checklist. Its weaknesses are length — much of the security, OGM, and subscriptions material should live in reference files like search-directives.md does — and the absence of explicit validation loops around destructive mutation workflows.

Suggestions

Move the Security (@authentication/@authorization) and OGM sections into separate reference files (e.g., references/security.md, references/ogm.md), keeping only the constructor/config essentials inline, to mirror the successful search-directives.md pattern and shrink the ~490-line body.

Add an explicit validation checkpoint after destructive or batch operations (e.g., 'after deleteMovies, verify counts with a query before proceeding') so workflows include a validate-then-proceed loop rather than relying only on the Common Errors table.

Trim the Schema Control Directives and Nested Mutations sections to one-line pointers plus a single example each; the full syntax can live in a reference file, reducing token cost without losing actionability.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious, version-pinned specifics (v7 explicit 'eq' syntax, breaking-changes table, security-patch versions) and confines time-sensitive version info to a Version Matrix / 'v6 → v7 Breaking Changes' section, with almost no padding of concepts Claude already knows. Not 5 because sections like Schema Control Directives and the OGM CRUD walkthrough could be trimmed or delegated without losing actionability.

4 / 5

Actionability

Fully executable throughout: copy-paste install commands, a complete minimal server setup, full directive syntax with annotated gotchas ('columnName must exactly match the RETURN alias — mismatch returns null silently'), a Common Errors table with cause/fix pairs, and a final checklist. Covers the common cases concretely.

5 / 5

Workflow Clarity

Sequenced steps ('Step 1 — Install', 'Step 2 — Minimal Server Setup', security Steps 1–3) plus checkpoints ('wrap in try/catch', the checklist, and the error-recovery table) give a clear sequence with most checkpoints present. Not 5 because destructive/batch operations (deletes, nested mutations) lack an explicit validate-after-operation loop — validation is implied via the error table rather than stated as validate-then-proceed steps.

4 / 5

Progressive Disclosure

The one bundle file (references/search-directives.md) is real, one level deep, and well signaled in two places, but the ~490-line body inlines substantial content that belongs in separate reference files (security/@authorization, OGM, subscriptions), leaving SKILL.md closer to a monolithic reference than an overview. This matches the level-3 anchor ('content that should be separate is inline') better than level 4.

3 / 5

Total

16

/

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.

An exemplary description: specific capabilities, an explicit 'Use when' trigger clause, and explicit out-of-scope redirects to sibling skills. The only minor weakness is that trigger coverage relies on precise technical terms rather than enumerated synonyms of phrasings a user might naturally say.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and APIs — 'Neo4jGraphQL constructor, getSchema(), assertIndexesAndConstraints(), type definitions with @node, @relationship... @cypher for custom resolvers, @authorization/@authentication... OGM programmatic access, subscriptions via CDC, and Apollo Federation' — with comprehensive coverage of the library's surface. It exceeds the level-4 anchor ('several specific actions; minor gaps') since no significant capability area is missing.

5 / 5

Completeness

Explicitly answers both: what — 'Build and configure a GraphQL API backed by Neo4j using @neo4j/graphql v7 (current) or v5 (LTS)' — and when — 'Use when writing typeDefs, securing fields, or wiring Neo4j to Apollo Server', matching the top anchor's what+when with concrete triggers.

5 / 5

Trigger Term Quality

'Use when writing typeDefs, securing fields, or wiring Neo4j to Apollo Server' plus natural terms like 'GraphQL API', 'JWT/JWKS', and the package name '@neo4j/graphql' give good keyword coverage. It falls short of level 5 because there is no synonym enumeration (e.g., 'generate a GraphQL schema from my graph', 'Neo4j GraphQL auth') as in the top anchor.

4 / 5

Distinctiveness Conflict Risk

'Does NOT handle raw Cypher outside resolvers — use neo4j-cypher-skill. Does NOT cover Spring Data Neo4j entity mapping — use neo4j-spring-data-skill' gives explicit negative boundaries and redirects, leaving a clear niche with minimal conflict risk.

5 / 5

Total

19

/

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-graphql-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.