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

94%

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

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 dense, highly actionable reference with executable examples, explicit write-gate validation, and error-recovery guidance. Its main weakness is conciseness: scattered inline version tags and a lightly padded aside could be consolidated into the deprecated section.

Suggestions

Consolidate time-sensitive version markers ([2025.11], [2026.03], [2026.02], [2026.04]) into a single 'Version history' or the existing 'Deprecated' section instead of scattering them inline, to keep the body evergreen.

Remove the 'Key insight (Bergman): shortest path...' aside or relocate it to the references file; it is conceptual commentary rather than actionable instruction.

Consider moving the Common Errors and full procedure-signature detail into references/providers.md (or a new references/api.md) to keep SKILL.md a tighter overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-heavy with little over-explanation, but inline time-sensitive version tags ([2025.11], [2026.03], [2026.04]) are scattered across sections rather than confined to the deprecated/old-patterns section, and the 'Key insight (Bergman)' aside is mild padding.	4 / 5
Actionability	Provides copy-paste-ready executable Cypher for every capability (embed, batch, completion, structured, chat, tokenCount, chunking, GraphRAG), with procedure signatures, return types, and a provider config table covering the common cases.	5 / 5
Workflow Clarity	The Write Gate gives an explicit sequenced workflow with validation checkpoints (count nodes, test one node, batch in transactions, require confirmation), the Common Errors table provides feedback loops, and a Checklist closes the process.	5 / 5
Progressive Disclosure	Good structure with clear sections and a well-signaled one-level reference (references/providers.md) that holds the full provider detail; however a fair amount of detailed API reference (signatures, error tables) is inlined in SKILL.md rather than split out.	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 strong, specific description that clearly states capabilities, trigger conditions, and boundaries against sibling skills. It uses third-person imperative voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (embedding generation, text completion, structured output, chat, tokenization, batch ingestion) plus the specific function names, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (the ai.text.* capabilities) and 'when' via a 'Use when...' clause with concrete trigger phrases, plus negative boundary guidance.	5 / 5
Trigger Term Quality	Includes natural user-facing terms like 'pure-Cypher GraphRAG', 'embedding nodes in-graph', 'generating structured maps from prompts', and 'calling LLMs inside Cypher queries' alongside provider names and synonyms.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (in-Cypher ai.text.* functions) and explicitly excludes overlapping skills ('Does NOT handle neo4j-graphrag Python library pipelines', 'Does NOT handle vector index creation/search'), minimizing conflict risk.	5 / 5
	Total	20 / 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: 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.