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.
76
96%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers specific capabilities with concrete function names, includes explicit 'Use when' triggers with natural domain terminology, and proactively disambiguates from related skills with clear boundary statements. It is a model example of a well-crafted description for a technical skill in a domain where multiple related skills could overlap.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and function names: embedding generation, text completion, structured output, chat, tokenization, batch ingestion, with explicit function references like ai.text.embed(), ai.text.embedBatch(), ai.text.completion(), etc. | 3 / 3 |
Completeness | Clearly answers both 'what' (lists all ai.text.* functions, provider configurations, and capabilities) and 'when' with explicit triggers ('Use when writing pure-Cypher GraphRAG, embedding nodes in-graph, generating structured maps from prompts, or calling LLMs inside Cypher queries'). Also includes explicit negative boundaries for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user working in this domain would use: 'Cypher', 'GraphRAG', 'embedding', 'LLMs inside Cypher queries', 'structured maps from prompts', 'OpenAI', 'Azure OpenAI', 'VertexAI', 'Amazon Bedrock', 'CYPHER 25', 'genai.vector.encode', and specific function names like 'ai.text.embed()'. These are highly natural for the target audience. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary statements ('Does NOT handle neo4j-graphrag Python library pipelines — use neo4j-graphrag-skill. Does NOT handle vector index creation/search — use neo4j-vector-index-skill.') that directly prevent conflicts with related skills. The specific function names and 'CYPHER 25' requirement further narrow the niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, highly actionable skill that covers a complex API surface with remarkable efficiency. Every function gets a concrete, executable Cypher example with proper parameterization and provider config. The Write Gate section with its validation steps, the deprecation table, the common errors table, and the final checklist demonstrate strong workflow awareness. The only minor weakness is that the file is fairly long and could benefit from splitting some advanced patterns into referenced files, and the one referenced bundle file (references/providers.md) is not provided.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is dense with information but every section earns its place. It avoids explaining what Neo4j, Cypher, or embeddings are, assumes Claude's competence, and jumps straight to signatures, config tables, and executable examples. No filler or unnecessary context. | 3 / 3 |
Actionability | Every function is demonstrated with complete, copy-paste-ready Cypher queries including proper CYPHER 25 prefixes, parameterized keys, and realistic patterns. The provider config table gives exact required keys. The Pure-Cypher GraphRAG pattern is a fully executable end-to-end example. | 3 / 3 |
Workflow Clarity | The 'Write Gate' section provides an explicit validation workflow: count nodes first, test with one node, batch with IN TRANSACTIONS, require confirmation. The common errors table serves as a troubleshooting checkpoint. The checklist at the end provides a comprehensive verification step. Feedback loops are present for bulk/destructive operations. | 3 / 3 |
Progressive Disclosure | The skill references 'references/providers.md' for full provider config, which is good progressive disclosure, but no bundle files are provided to verify this exists. The main file is quite long (~250+ lines) and some content like the full GraphRAG pattern or detailed structured completion examples could potentially be split out. However, the section organization with clear headers is solid. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- neo4j-contrib/neo4j-skills
- Commit
66ed0e1
- 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.