CtrlK
BlogDocsLog inGet started
Tessl Logo

neo4j-kafka-skill

Configure and operate the Neo4j Connector for Kafka (sink + source) and the native Neo4j CDC API. Covers Cypher/Pattern/CUD sink strategies, CDC-based and query-based source, exactly-once semantics, DLQ error handling, Confluent Cloud managed connector, schema registry (Avro/JSON), and native db.cdc.query cursor-loop patterns (Neo4j 5.13+ Enterprise/Aura BC/VDC). Use when streaming Kafka events into Neo4j, streaming Neo4j changes to Kafka, or querying Neo4j change events without Kafka. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT handle bulk CSV/file import — use neo4j-import-skill. Does NOT handle GDS algorithms — use neo4j-gds-skill.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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, highly actionable skill body with executable config/code, sequenced workflows, error-recovery guidance, and a validation checklist. Its main weakness is redundancy between inlined reference-grade detail and the existing bundle files, which slightly hurts conciseness and progressive disclosure.

Suggestions

Move the full Event Structure block and Selector Reference table into references/cdc-api.md, leaving a brief inline summary and a pointer — this trims the overview and tightens progressive_disclosure to one level deep.

Defer the complete per-property sink config reference to references/sink-config.md, keeping only the decision table and one canonical example per strategy in the body.

Consider compressing the duplicated 'Core Connection Config' block that reappears inside the sink and source examples to a single shared snippet referenced by anchor.

DimensionReasoningScore

Conciseness

Mostly lean and information-dense with no basic-concept padding, but the ~430-line body inlines reference-grade material (full Event Structure block, Selector Reference table) that overlaps the provided reference files and could be trimmed from the overview.

4 / 5

Actionability

Copy-paste-ready JSON config, Cypher, and a complete Python cursor-loop cover the common cases (sink strategies, CDC/query source, native CDC, schema registry, DLQ, Confluent Cloud) with fully executable guidance.

5 / 5

Workflow Clarity

EOS setup is sequenced as Step 1 (constraint) / Step 2 (config), the cursor loop includes 'advance cursor only after successful processing', the Common Errors table gives error-recovery feedback loops, and a closing Checklist validates the batch/destructive operations.

5 / 5

Progressive Disclosure

Two real one-level-deep references (references/sink-config.md, references/cdc-api.md) are clearly signaled in a References section, but significant detail (Event Structure, Selector Reference) is inlined in the body rather than delegated to those files, leaving minor organization gaps.

4 / 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 strong, third-person description that names concrete capabilities, gives explicit 'Use when' triggers, and routes adjacent work to sibling skills via clear 'Does NOT handle' boundaries. Comprehensive and distinct with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Configure and operate the Neo4j Connector for Kafka (sink + source)', 'Cypher/Pattern/CUD sink strategies', 'exactly-once semantics, DLQ error handling, Confluent Cloud managed connector, schema registry (Avro/JSON)' — with comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly answers both what ('Configure and operate... Covers Cypher/Pattern/CUD sink strategies...') and when ('Use when streaming Kafka events into Neo4j, streaming Neo4j changes to Kafka, or querying Neo4j change events without Kafka') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrases like 'streaming Kafka events into Neo4j', 'streaming Neo4j changes to Kafka', and 'querying Neo4j change events without Kafka' plus synonyms (sink/source, CDC) give comprehensive coverage of terms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Neo4j Kafka connector + native CDC) with explicit routing — 'Does NOT handle Cypher query authoring — use neo4j-cypher-skill', 'Does NOT handle bulk CSV/file import', 'Does NOT handle GDS algorithms' — minimizing conflict risk.

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.