CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

neo4j-cypher-skill

Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x. Use when writing new Cypher queries, optimizing slow queries, graph pattern matching, vector or fulltext search, subqueries, or batch writes. Covers MATCH, MERGE, CREATE, WITH, RETURN, CALL, UNWIND, FOREACH, LOAD CSV, SEARCH, expressions, functions, indexes, and subqueries. Does NOT handle driver migration or API changes — use neo4j-migration-skill. Does NOT cover DB administration or server ops — use neo4j-cli-tools-skill.

94

2.04x
Quality

93%

Does it follow best practices?

Impact

100%

2.04x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 very strong skill body: terse, version-aware guidance Claude could not reconstruct from general knowledge, fully executable examples, and a complete validation workflow with a write gate. The only improvement area is trimming Key Patterns subsections that duplicate cypher-syntax.md content.

Suggestions

Trim the Key Patterns subsections whose content is already promised by references/cypher-syntax.md (string interpolation, UUID type, map-related notes) down to one-line pointers, keeping only the highest-frequency patterns inline.

Move the multi-row Version Gates fallbacks for rarely needed features (e.g. GQL function aliases, map comprehension) into a version-compat reference file, keeping only the most common gates in SKILL.md.

Consider shortening the Spatial/Point subsection to the bounding-box pattern plus a pointer, since point() function semantics are standard knowledge.

DimensionReasoningScore

Conciseness

The body is extremely dense and telegraphic with no concept-padding (no "what is a graph database" prose), and version-sensitive detail is properly concentrated in a Version Gates table with fallbacks rather than scattered. However, several Key Patterns subsections (UUID, spatial/point, string interpolation, GROUP BY) inline material that the reference list says cypher-syntax.md already covers, which could be trimmed from the overview.

4 / 5

Actionability

Fully executable guidance throughout: complete Cypher code blocks with CYPHER 25 prefixes and parameters, exact SHOW/CALL schema-inspection commands, a copy-paste curl example for Query API v2, and a wrong/right trap table with concrete replacements. This matches the copy-paste-ready, common-cases-covered anchor.

5 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced with explicit validation checkpoints: the Pre-flight decision table, the Schema-First Protocol priority order, a validation workflow ("EXPLAIN before any write", test reads with LIMIT 1, verify write half as RETURN before SET/CREATE/DELETE, PROFILE for db hits), a write execution gate requiring user confirmation, a failure-recovery section, and a final checklist. Validation for destructive/batch operations is present, so the workflow cap does not apply.

5 / 5

Progressive Disclosure

The body works as a well-structured overview with a dedicated "References — Load on demand" section where each of the seven reference files is described, and all referenced paths (plus the three scripts) exist as real one-level-deep files. Only the top syntax traps are inlined with "Full trap table → references/syntax-traps.md", showing appropriate splitting between overview and detail.

5 / 5

Total

19

/

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 excellent description: concrete actions, explicit use-when triggers, enumerated coverage, and proactive routing away to sibling skills. The only minor gap is a few missing natural synonyms for query-writing/tuning requests.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — "Generates, optimizes, and validates Cypher 25 queries" — and comprehensively enumerates covered clauses ("MATCH, MERGE, CREATE, WITH, RETURN, CALL, UNWIND, FOREACH, LOAD CSV, SEARCH") and feature areas. Coverage of actions has no meaningful gaps, matching the comprehensive anchor.

5 / 5

Completeness

Both questions are explicitly answered: the what ("Generates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x") and the when ("Use when writing new Cypher queries, optimizing slow queries, …") with concrete trigger phrases, plus explicit negative scope. This matches the anchor for clearly answering both what and when.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are well represented: "writing new Cypher queries", "optimizing slow queries", "vector or fulltext search", "batch writes", "graph pattern matching". A few common synonyms/variations are missing (e.g. "query performance", "Neo4j query help", "graph database"), so it sits just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Cypher queries for a named product/version range) with explicit disambiguation — "Does NOT handle driver migration or API changes — use neo4j-migration-skill" and "Does NOT cover DB administration or server ops — use neo4j-cli-tools-skill" — making wrong-skill triggering minimal.

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-cypher-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.