neo4j-vector-index-skill

Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings on nodes or relationships, use SEARCH clause (Neo4j 2026.01+, preferred) or db.index.vector.queryNodes() procedure (deprecated 2026.04, still works on 2025.x), configure HNSW and quantization options, pick similarity function and embedding provider dimensions, and batch-update embeddings. Use when tasks involve CREATE VECTOR INDEX, vector.dimensions, cosine/euclidean search, embedding ingestion pipelines, semantic or structural nearest-neighbor lookup, or hybrid search (vector + fulltext, multiple vector sources, or graph-derived scores). Does NOT handle GraphRAG retrieval_query graph traversal — use neo4j-graphrag-skill. Does NOT handle fulltext-only/keyword-only search — use neo4j-cypher-skill. Does NOT compute GDS graph embeddings (FastRP, Node2Vec) — use neo4j-gds-skill.

2.63x

Quality

94%

Does it follow best practices?

Impact

100%

2.63x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 thorough, highly actionable skill body with a clear sequenced workflow, strong validation checkpoints, and good use of a single on-demand reference. Minor conciseness costs come from redundant 'Extended' sections and scattered version annotations that could be consolidated.

Suggestions

Consolidate the 'Similarity Function — Extended Guidance' and 'Gotchas — Extended' sections into the existing Step 1 / Common Errors material to remove restated content.

Group version-gated features (2025.10+, 2025.20+, 2026.06+) into a dedicated 'Version compatibility' or 'Deprecated/old patterns' section rather than scattering inline tags.

Consider moving the extended gotchas table into a reference file to keep SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code/table-driven assuming Claude's competence, but the 'Similarity Function — Extended Guidance' and 'Gotchas — Extended' sections restate Step 1 / Common Errors content, and many inline version tags (2025.10+, 2025.20+, 2026.06+) could be consolidated into a deprecated/old-patterns section.	4 / 5
Actionability	Copy-paste-ready Cypher and Python across all common cases — index creation variants, ONLINE polling, batch UNWIND ingest, SEARCH and procedure search, vector functions, and index management — with specific parameters and complete examples.	5 / 5
Workflow Clarity	Clear numbered Pre-flight → Step 1-6 sequence with explicit validation checkpoints ('do NOT query until ONLINE', poll every 5s, dimension assert before ingest, 'Never create index after embeddings') plus an error→cause→fix table and a final checklist providing feedback loops for batch/database operations.	5 / 5
Progressive Disclosure	Well-sectioned overview with a clearly signaled one-level-deep reference ('Load references/hybrid-search.md and apply its query shape') and an on-demand References list; the body is large and some 'Extended' subsections are inlined rather than split out, keeping it just short of the top anchor.	4 / 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.

A dense, highly specific description that concretely states capabilities, surfaces natural trigger terms, and explicitly demarcates boundaries against three sibling skills. It fully answers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings', 'configure HNSW and quantization options, pick similarity function and embedding provider dimensions, and batch-update embeddings' — covering the domain comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (the opening action list) and 'when' ('Use when tasks involve...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Covers the natural terms a Neo4j user would say — 'CREATE VECTOR INDEX, vector.dimensions, cosine/euclidean search, embedding ingestion pipelines, semantic or structural nearest-neighbor lookup, or hybrid search' — including synonyms and procedure/API names.	5 / 5
Distinctiveness Conflict Risk	Three explicit 'Does NOT handle... use <sibling-skill>' boundary clauses carve a clear niche with minimal conflict risk against GraphRAG, fulltext, and GDS skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: neo4j-contrib/neo4j-skills
Path: neo4j-vector-index-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.