graphrag-patterns
GraphRAG implementation patterns for hybrid search, Text2Cypher, and agentic retrieval. Use when implementing RAG workflows with Neo4j.
npx skills add majiayu000/claude-skill-registry --skill graphrag-patterns --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# GraphRAG Patterns ## Hybrid Search (Vector + Keyword) Combine vector similarity with full-text search for better recall: ```python from langchain_neo4j import Neo4jVector def create_hybrid_retriever(driver, embeddings): return Neo4jVector.from_existing_graph( embeddings, driver=driver, index_name="article_embeddings", keyword_index_name="article_fulltext", search_type="hybrid", # Combines vector + keyword node_label="Article", text_node_properties=["content", "summary"], embedding_node_property="embedding", ) ``` ## Text2Cypher with Few-Shot Examples Always provide examples for better query generation: ```python FEW_SHOT_EXAMPLES = [ { "question": "What articles discuss requirements traceability?", "cypher": ''' MATCH (a:Article) WHERE a.content CONTAINS 'traceability' RETURN a.title, a.summary LIMIT 10 ''' }, { "question": "Which chapters have the most articles?", "cypher": ''' MATCH (c:Chapter)-[:CONTAINS]->(a:Article) RETURN c.title, count(a) as article_count ORDER BY article_count DESC ''' }, ] from langchain_neo4j import GraphCypherQAChain chain = GraphCypherQAChain.from_llm( llm=llm, graph=graph, cypher_prompt=CYPHER_PROMPT, example_selector=SemanticSimilarityExampleSelecto
- Hybrid Search (Vector + Keyword)
- Text2Cypher with Few-Shot Examples
- Agentic Router Pattern
- Graph-Enriched Retrieval
- RAGAS Evaluation Metrics
- Stepback Prompting
What does the graphrag-patterns skill do?
GraphRAG implementation patterns for hybrid search, Text2Cypher, and agentic retrieval. Use when implementing RAG workflows with Neo4j.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill graphrag-patterns --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.