neo4j-import-skill

Import structured data into Neo4j — LOAD CSV, CALL IN TRANSACTIONS, neo4j-admin database import full (offline bulk), apoc.load.csv/json, apoc.periodic.iterate, driver batch writes. Covers method selection, header file format, type coercion, null handling, ON ERROR modes, CONCURRENT TRANSACTIONS, pre-import constraint setup, and post-import validation. Use when importing CSV/JSON/Parquet files, migrating relational data to graph, or bulk-loading large datasets. Does NOT handle unstructured document/PDF/vector chunking pipelines — use neo4j-document-import-skill. Does NOT handle live app write patterns (MERGE/CREATE) — use neo4j-cypher-skill. Does NOT handle neo4j-admin backup/restore/config — use neo4j-cli-tools-skill.

1.26x

Quality

88%

Does it follow best practices?

Impact

96%

1.26x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

100%

23%

Importing a Movie Reviews Dataset into Neo4j

LOAD CSV online import script with null handling and batch config

Criteria

Without context

With context

CYPHER 25 prefix

100%

Constraints before import

100%

CALL IN TRANSACTIONS used

100%

ON ERROR CONTINUE

100%

REPORT STATUS

100%

toIntegerOrNull usage

33%

100%

toFloatOrNull usage

33%

100%

Empty-string null handling

100%

Nodes before relationships

100%

Relationship batch size 5000

75%

100%

Post-import count queries

100%

Index poll query

83%

100%

92%

Bulk Loading a Large E-Commerce Catalog into Neo4j

neo4j-admin offline bulk import with header files and SSD flags

Criteria

Without context

With context

neo4j-admin import command

100%

Node :ID column

100%

Node :LABEL column

62%

50%

Typed property columns

100%

Datetime type annotation

100%

Relationship :START_ID and :END_ID

100%

Relationship :TYPE column

57%

42%

--high-parallel-io=on flag

100%

--bad-tolerance=0 flag

100%

--threads flag

100%

Nodes before relationships

100%

Correct database target

100%

96%

31%

Migrating GitHub Repository Data from API into Neo4j

Python driver batch write with UNWIND and BATCH_SIZE=10000

Criteria

Without context

With context

BATCH_SIZE = 10000

100%

UNWIND $rows pattern

100%

execute_write for batches

100%

Batch loop collects chunks

100%

Constraints before import

100%

Nodes before relationships

100%

Null-safe integer handling

40%

60%

driver.close() called

100%

MERGE not CREATE

100%

Prefer driver over APOC

100%

Database parameter specified

100%

Repository: neo4j-contrib/neo4j-skills
Commit: 66ed0e1

Evaluated: about 23 hours ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Importing a Movie Reviews Dataset into Neo4j Bulk Loading a Large E-Commerce Catalog into Neo4j Migrating GitHub Repository Data from API into Neo4j

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.