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.

1.35x

Quality

96%

Does it follow best practices?

Impact

77%

1.35x

Average score across 2 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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.

The body is a high-quality reference skill: densely executable, with a clearly sequenced pre-import workflow and validation checkpoints, and well-structured progressive disclosure to real bundle files. The only soft spot is conciseness, where dense version annotations and a few redundant notes could be tightened.

Suggestions

Consolidate the scattered inline version annotations (e.g. '[2026.07+]', '[2026.06+]', '[2025.12]') into a single 'Version notes' or 'Deprecated/old patterns' section so the main flow stays lean — the rubric penalizes time-sensitive inline notes that aren't isolated.

Trim a few redundant table note cells (e.g. repeated restatements of the constraints-before/indexes-after rule) to push conciseness from 4 toward 5.

Consider moving the detailed ON ERROR mode semantics or the cloud-storage scheme table into a reference file if the main SKILL.md is meant to stay an overview, reducing inline density.

Dimension	Reasoning	Score
Conciseness	Mostly lean — tables and code blocks with no padding about concepts Claude already knows — but dense inline version annotations (e.g. '[2026.07+]', '[2026.06+]') and a few slightly redundant table notes could be trimmed. It sits noticeably above the 'mostly efficient' (3) anchor but not fully at the 'every token earns its place' (5) level.	4 / 5
Actionability	Fully executable throughout: complete LOAD CSV + CALL IN TRANSACTIONS Cypher, a runnable neo4j-admin command with all key flags, concrete header-file examples, and copy-paste driver batch-write code (delegated to references) covering the common import cases.	5 / 5
Workflow Clarity	The Pre-Import Checklist is explicitly ordered ('Run in this exact order'), enforces constraints-before/indexes-after, and includes validation checkpoints (REPORT STATUS, poll populationPercent to 100, post-import count/null-key checks) plus a write-confirmation gate and a terminal checklist — feedback loops appropriate for batch/destructive import.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with clearly signaled one-level-deep references to real bundle files (driver-batch-write.md, data-importer-gui.md, post-import-refactoring.md) and sibling-skill references; executable detail is appropriately offloaded, making navigation easy.	5 / 5
	Total	19 / 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.

The description is precise, concrete, and self-disambiguating: it names the specific import methods, gives explicit 'Use when' triggers with file formats, and clearly carves out boundaries against related skills. It is among the strongest examples in the rubric's reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'LOAD CSV', 'CALL IN TRANSACTIONS', 'neo4j-admin database import full (offline bulk)', 'apoc.load.csv/json', 'apoc.periodic.iterate', 'driver batch writes' — plus sub-topics like 'header file format, type coercion, null handling, ON ERROR modes', giving comprehensive coverage of concrete import capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated import methods and covered concerns) and 'when' via 'Use when importing CSV/JSON/Parquet files, migrating relational data to graph, or bulk-loading large datasets', with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including file types/extensions ('CSV/JSON/Parquet files') and synonyms ('importing', 'migrating relational data to graph', 'bulk-loading large datasets'); a user needing this skill would naturally say these phrases.	5 / 5
Distinctiveness Conflict Risk	A clear niche (structured data import into Neo4j) with three explicit 'Does NOT handle' boundary clauses redirecting unstructured docs, live app writes, and admin backup/restore to sibling skills, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (501 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: neo4j-contrib/neo4j-skills
Path: neo4j-import-skill/SKILL.md
Commit: a9a5e78

Reviewed: 6 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.