neo4j-query-tuning-skill

Diagnoses and fixes slow Neo4j Cypher queries by reading execution plans, identifying bad operators (AllNodesScan, CartesianProduct, Eager, NodeByLabelScan), and prescribing fixes (indexes, hints, query rewrites, runtime selection). Use when a query is slow, when EXPLAIN or PROFILE output needs interpretation, when dbHits or pageCacheHitRatio are poor, when cardinality estimation diverges from actuals, or when deciding between slotted/pipelined/parallel runtimes. Covers USING INDEX / USING SCAN / USING JOIN hints, db.stats.retrieve, SHOW QUERIES, SHOW TRANSACTIONS, TERMINATE TRANSACTION. Does NOT write new Cypher from scratch — use neo4j-cypher-skill. Does NOT cover GDS algorithm tuning — use neo4j-gds-skill. Does NOT cover index/constraint creation syntax details — use neo4j-cypher-skill references/indexes.md.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

86%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.

A dense, actionable skill body with executable Cypher throughout, a well-sequenced diagnostic runbook, and clean one-level-deep references to real bundle files. Minor trimming of operator-table redundancy and a confirm step before TERMINATE would push it to top marks.

Suggestions

Move the full operator table to references/plan-operators.md and keep only the most common good/bad operators inline to reduce duplication with the referenced file.

Add an explicit validation/confirmation checkpoint before TERMINATE TRANSACTION and TERMINATE QUERY (e.g., verify the target queryId/transactionId against SHOW QUERIES output before killing).

Relocate time-sensitive version markers like '[2026.03]' and 'Aura Pro 2025+' into a dedicated 'Version notes' or 'Deprecated/old patterns' section so they do not clutter the evergreen guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and task-specific reference material with little padding of concepts Claude already knows, but the inline operator table partially duplicates the referenced plan-operators.md and scattered version markers ('[2026.03]', 'Aura Pro 2025+') sit outside a deprecated section.	4 / 5
Actionability	Copy-paste-ready Cypher for SHOW INDEXES, CREATE INDEX (RANGE/TEXT/composite), USING INDEX/SCAN/JOIN hints, CALL IN TRANSACTIONS, runtime selection, and TERMINATE commands — concrete examples cover the common tuning cases.	5 / 5
Workflow Clarity	A clear 5-step diagnostic runbook with validation checkpoints (profile-after-fix dbHits comparison, replanning check) and a closing checklist, but destructive ops like TERMINATE TRANSACTION lack an explicit confirm-before-kill checkpoint.	4 / 5
Progressive Disclosure	Overview and quick-reference tables are inline while bulk material is one level deep in real, clearly-signaled files — 'Full operator reference → references/plan-operators.md' and 'Full monitoring reference → references/stats-and-monitoring.md' — both of which exist in the bundle.	5 / 5
	Total	18 / 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.

A highly specific, third-person description that clearly states capabilities, gives concrete 'Use when' triggers, and disambiguates from sibling skills via explicit 'Does NOT' boundaries. It is a strong model description with no notable gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reading execution plans, identifying bad operators (AllNodesScan, CartesianProduct, Eager, NodeByLabelScan), and prescribing fixes (indexes, hints, query rewrites, runtime selection)' — with comprehensive coverage of the tuning task.	5 / 5
Completeness	Explicitly answers both what (diagnose/fix slow queries, read plans, identify operators, prescribe fixes, cover hints and monitoring) and when (explicit 'Use when...' clauses), plus boundary 'Does NOT' clauses.	5 / 5
Trigger Term Quality	Multiple natural trigger phrases a Neo4j user would actually say — 'query is slow', 'EXPLAIN or PROFILE output needs interpretation', 'dbHits or pageCacheHitRatio are poor', 'cardinality estimation diverges from actuals', 'deciding between slotted/pipelined/parallel runtimes' — with synonyms and operator names.	5 / 5
Distinctiveness Conflict Risk	Clear Neo4j-query-tuning niche with explicit 'Does NOT' boundary clauses routing sibling work to neo4j-cypher-skill, neo4j-gds-skill, and neo4j-cypher-skill references/indexes.md, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: neo4j-contrib/neo4j-skills
Path: neo4j-query-tuning-skill/SKILL.md
Commit: 02ad354

Reviewed: 3 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.