CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

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 highly actionable, well-sequenced with validation checkpoints, and uses progressive disclosure effectively by offloading full operator and monitoring references to real bundle files. The only minor weakness is a few sections of light over-explanation that could be trimmed for token efficiency.

Suggestions

Trim the prose paragraphs under Cypher Runtime Selection (e.g., the pipelined/slotted/parallel narrative) and the curl Query API example — keep only the table and the inline forcing example to tighten token usage.

The EXPLAIN vs PROFILE table repeats concepts Claude already knows; consider condensing to a single line stating the key actionable rule (run PROFILE twice, first warms cache) and which metrics each exposes.

Remove tutorial-style notes like "Read plans bottom-up — leaf operators at bottom initiate data retrieval" if the same guidance is covered in references/plan-operators.md, to avoid duplicate explanation.

DimensionReasoningScore

Conciseness

Mostly lean and action-oriented — dense tables and code blocks assume Claude's competence and avoid explaining basics like "what Neo4j is". Minor instances of over-explanation remain (e.g., the prose around runtime selection and the curl Query API example), so it falls just below a perfect lean score.

4 / 5

Actionability

Fully executable, copy-paste-ready Cypher throughout — index creation, USING INDEX/SCAN/JOIN hints, CartesianProduct and Eager fix strategies, runtime selection, and monitoring/terminate commands — covering the common diagnostic cases concretely.

5 / 5

Workflow Clarity

A clear 5-step "Diagnostic Workflow (Agent Runbook)" sequence (baseline → check indexes → create → profile → replan) with explicit validation checkpoints ("wait for state = 'ONLINE' before measuring", "Compare dbHits and elapsed ms before/after") and a closing checklist providing feedback loops for the database operations involved.

5 / 5

Progressive Disclosure

SKILL.md serves as a well-organized overview with two clearly signaled, one-level-deep references to real bundle files — operator reference → references/plan-operators.md and monitoring → references/stats-and-monitoring.md — with bulk detail appropriately split out.

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 exemplary: it states concrete diagnostic and fix actions, provides rich natural trigger terms, explicitly covers both what and when, and uses explicit "Does NOT" boundaries to avoid conflicts with sibling skills. No improvements needed.

DimensionReasoningScore

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 skill's capabilities.

5 / 5

Completeness

Explicitly answers both: what it does ("Diagnoses and fixes slow Neo4j Cypher queries...") and when to use it ("Use when a query is slow, when EXPLAIN or PROFILE output needs interpretation...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural and technical triggers users would say: "query is slow", "EXPLAIN or PROFILE output needs interpretation", "dbHits or pageCacheHitRatio are poor", "cardinality estimation diverges", "slotted/pipelined/parallel runtimes", plus commands like SHOW QUERIES and TERMINATE TRANSACTION.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Neo4j Cypher query tuning) reinforced by three explicit "Does NOT" boundary statements steering sibling tasks to neo4j-cypher-skill, neo4j-gds-skill, and neo4j-modeling-skill, minimizing wrong-skill triggering.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
neo4j-contrib/neo4j-skills
Reviewed

Table of Contents

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.