neo4j-genai-plugin-skill

Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher embedding generation, text completion, structured output, chat, tokenization, and batch ingestion. Covers ai.text.embed(), ai.text.embedBatch(), ai.text.completion(), ai.text.structuredCompletion(), ai.text.aggregateCompletion(), ai.text.chat(), ai.text.tokenCount(), ai.text.chunkByTokenLimit(), and provider configuration for OpenAI, Azure OpenAI, VertexAI, and Amazon Bedrock. Requires CYPHER 25. Replaces deprecated genai.vector.encode(). Use when writing pure-Cypher GraphRAG, embedding nodes in-graph, generating structured maps from prompts, or calling LLMs inside Cypher queries. Does NOT handle neo4j-graphrag Python library pipelines — use neo4j-graphrag-skill. Does NOT handle vector index creation/search — use neo4j-vector-index-skill.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

82%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 executable Cypher examples for every function and solid validation guidance for batch writes. Minor room for improvement in consolidating time-sensitive version markers and splitting more detail into reference files.

Suggestions

Move inline version markers like [2025.11]/[2026.04] into a dedicated versioning or deprecated section, or strip them from prose, to reduce time-sensitive token overhead in the main body.

Add an explicit fix-and-revalidate feedback loop to the Write Gate (e.g. 'if the test node embed returns null, fix config and re-test before proceeding to the batch') so batch operations have a clear recovery path.

Consider extracting the per-function code galleries (Embedding, Structured Output, Chat) into a references/examples.md file, keeping only one representative example per capability inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly lean, code-first content that assumes Claude's competence, but scattered inline time-sensitive version markers ([2025.11], [2026.02], [2026.03], [2026.04]) and the editorial 'Key insight (Bergman)' aside are minor trim candidates not housed in the deprecated section.	4 / 5
Actionability	Provides fully executable, copy-paste-ready Cypher examples for every supported function (embed, embedBatch, completion, aggregateCompletion, structuredCompletion, chat, tokenCount, chunkByTokenLimit, GraphRAG) with documented signatures covering the common cases.	5 / 5
Workflow Clarity	The Write Gate gives a clear sequenced process with validation checkpoints (count nodes, test one node, IN TRANSACTIONS batches, explicit confirmation) and a Common Errors table for recovery, but there is no explicit fix-and-revalidate feedback loop for bulk writes.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with a clearly signaled one-level-deep reference (references/providers.md) and external doc links; however most detailed per-function examples live inline rather than being split into separate reference files, a minor organization gap.	4 / 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 states capabilities, enumerates the exact functions covered, gives concrete use-when triggers, and explicitly boundaries the skill against neighboring Neo4j skills. Trigger-term coverage is the only minor weakness, missing a few natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (embedding generation, text completion, structured output, chat, tokenization, batch ingestion) and enumerates the exact functions covering them, giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly states both what it does (in-Cypher embedding/completion/structured/chat/tokenization) and when to use it ('Use when writing pure-Cypher GraphRAG, embedding nodes in-graph...') with concrete trigger phrases, plus explicit when-not-to-use boundaries.	5 / 5
Trigger Term Quality	Includes natural developer-facing phrases like 'pure-Cypher GraphRAG', 'embedding nodes in-graph', and 'calling LLMs inside Cypher queries'; a few common synonyms or phrasings (e.g. 'RAG', 'vector embeddings') are not covered.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche and explicitly disambiguates adjacent skills ('Does NOT handle neo4j-graphrag Python library pipelines — use neo4j-graphrag-skill'; 'Does NOT handle vector index creation/search — use neo4j-vector-index-skill'), minimizing 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-genai-plugin-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.