AGENT SKILL

neo4j-query

Query Neo4j knowledge graph for entities, relationships, and graph analysis.

License 许可
MIT
最近更新
2026-04-09
Stars
★ 245
Forks
15

01 前言 Front Matter

name
neo4j-query
triggers
[ "neo4j", "knowledge graph", "entities", "relationships", "graph query", "cypher" ]
description
Query Neo4j knowledge graph for entities, relationships, and graph analysis.

03 SKILL.md 正文

Neo4j Query Skill

Query the Neo4j knowledge graph to investigate entities, relationships, and graph structure.

Connection Details

  • URI: bolt://localhost:7687 (or NEO4J_URI env var)
  • User: neo4j (or NEO4J_USER env var)
  • Password: refinerypass (or NEO4J_PASSWORD env var)

Python Usage

from qq.knowledge.neo4j_client import Neo4jClient

# Initialize client
client = Neo4jClient()

# Execute raw Cypher query
results = client.execute("MATCH (n) RETURN n LIMIT 10")

# Get graph summary (entity and relationship counts by type)
summary = client.get_graph_summary()

# Get entity by name
entity = client.get_entity("entity_name")

# Get related entities (up to N hops)
related = client.get_related_entities("entity_name", depth=2, limit=20)

# Close when done
client.close()

Common Cypher Queries

Count entities and relationships

-- Total entities
MATCH (n) RETURN count(n) as total_entities

-- Entities by type
MATCH (n) RETURN labels(n)[0] as type, count(n) as count ORDER BY count DESC

-- Total relationships
MATCH ()-[r]->() RETURN count(r) as total_relationships

-- Relationships by type
MATCH ()-[r]->() RETURN type(r) as type, count(r) as count ORDER BY count DESC

Find orphan entities (no relationships)

-- Entities with no incoming or outgoing relationships
MATCH (n) WHERE NOT (n)--() RETURN n.name, labels(n)[0] as type

Analyze connectivity

-- Entities with most connections
MATCH (n)-[r]-() RETURN n.name, labels(n)[0] as type, count(r) as connections ORDER BY connections DESC LIMIT 10

-- Distribution of relationship counts per entity
MATCH (n)
OPTIONAL MATCH (n)-[r]-()
WITH n, count(r) as rel_count
RETURN rel_count, count(n) as entities_with_this_count ORDER BY rel_count

Sample entities and relationships

-- Sample entities with their properties
MATCH (n) RETURN n.name, labels(n)[0] as type, n.description LIMIT 20

-- Sample relationships with endpoints
MATCH (a)-[r]->(b) RETURN a.name, type(r), b.name LIMIT 20

CLI Usage

# Use cypher-shell directly
docker exec -it qq-neo4j-1 cypher-shell -u neo4j -p refinerypass "MATCH (n) RETURN count(n)"

04 同仓库更多 Skills

OriNachum
OriNachum/autonomous-intelligence

test

Run TTS round-trip tests — pure-logic unit tests and optional integration tests against live TTS/STT services.

测试与质量
★ 245
OriNachum
OriNachum/autonomous-intelligence

speak

Speak text aloud using the Magpie TTS container in the realtime-api Docker stack. Zero external dependencies — just curl + aplay.

★ 245
OriNachum
OriNachum/autonomous-intelligence

deploy

Build and deploy the realtime-api Docker container with full verification that deployed code matches local source.

开发工程师运维与部署
★ 245
OriNachum
OriNachum/autonomous-intelligence

memory

Unified memory management for notes, knowledge graph, RAG search, and file analysis. Use when working with: (1) Core memory — protected identity, projects, relationships, and system facts that should never be forgotten, (2) Working notes — per-session ephemeral notes organized by section, (3) MongoDB RAG — vector-search-enabled notes with importance scoring, decay, deduplication, and archival, (4) Neo4j knowledge graph — entities, relationships, merge duplicates, reinforce mentions, Cypher queries, (5) File analysis — deep file reading that extracts knowledge into all memory layers, (6) Service initialization — health-check, start/stop MongoDB, Neo4j, TEI embeddings via docker-compose with partial setup support.

运维与部署资料检索与研究
★ 245
OriNachum
OriNachum/autonomous-intelligence

coding

Enhanced coding assistance

开发工程师
★ 245
OriNachum
OriNachum/autonomous-intelligence

memory

Unified memory management for notes, knowledge graph, RAG search, and file analysis. Use when working with: (1) Core memory — protected identity, projects, relationships, and system facts that should never be forgotten, (2) Working notes — per-session ephemeral notes organized by section, (3) MongoDB RAG — vector-search-enabled notes with importance scoring, decay, deduplication, and archival, (4) Neo4j knowledge graph — entities, relationships, merge duplicates, reinforce mentions, Cypher queries, (5) File analysis — deep file reading that extracts knowledge into all memory layers, (6) Service initialization — health-check, start/stop MongoDB, Neo4j, TEI embeddings via docker-compose with partial setup support.

运维与部署资料检索与研究
★ 245