CtrlK
BlogDocsLog inGet started
Tessl Logo

kafka-connector-v4

Set up, configure, and troubleshoot the Snowflake Kafka Connector V4 (Snowpipe Streaming high-performance architecture). Covers fresh installations, connector property configuration for default pipe and user-defined pipe modes, server-side and client-side validation, JMX monitoring, migration from V3, and common error diagnosis. Triggers: kafka connector v4, kafka connector setup, kafka connector config, kafka connector troubleshoot, snowflake kafka connector, configure kafka connector, kafka connector help, kafka streaming connector.

86

1.03x
Quality

81%

Does it follow best practices?

Impact

98%

1.03x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers excellent concrete, executable guidance with a well-sequenced, branchable workflow and thorough troubleshooting coverage. Its weaknesses are structural: an ~860-line monolithic file that inlines material better split into reference files, notable internal duplication, and a couple of cross-reference/typo defects.

Suggestions

Move the Templates section (Templates 1-12), the Step 8 troubleshooting catalog, and the Step 9 migration guide into separate reference files under references/ (e.g., references/templates.md, references/troubleshooting.md, references/migration.md), keeping SKILL.md as a concise overview with well-signaled links.

Deduplicate repeated content: the Step 2 SQL vs Template 4 overlap, the pipe-mode/validation-mode explanations in Critical Concepts vs Steps 6-7, and the ERROR_5030/DLQ incompatibility caveat stated in three places.

Fix the broken cross-reference in Step 6 ('see monitoring section in Critical Concepts' should point to Template 10) and the malformed error-table identifier in the ERROR_5030 symptom branch ('{{DATABASE}}.{{SCHEMA}."{{TABLE}}_ERRORS"').

DimensionReasoningScore

Conciseness

The body is mostly purposeful product-specific detail (V4 defaults, removed V3 properties, ERROR_5030 semantics) that Claude cannot know, but at ~860 lines it carries real redundancy: Step 2's SQL is duplicated nearly verbatim in Template 4, the pipe-mode and validation-mode explanations appear in both Critical Concepts and Steps 6-7, and the ERROR_5030/DLQ incompatibility caveat is stated in Step 7, the validation-modes section, and Step 8. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 4, where only minor instances would remain.

3 / 5

Actionability

Guidance is largely copy-paste ready — 12 complete config/SQL/query templates, concrete bash and curl commands, exact property names — covering the common cases. It falls just short of the level-5 anchor due to minor gaps: the error-table query contains a malformed identifier ('{{DATABASE}}.{{SCHEMA}."{{TABLE}}_ERRORS"' — missing closing brace), and the standalone startup command uses an abstract '<kafka_dir>' placeholder. Still clearly above level 3, where guidance would be pseudocode or missing key details.

4 / 5

Workflow Clarity

Steps 0-9 are clearly sequenced with intent-based branching, per-step goals, error handling in Step 1, verification in Step 5, and symptom-based diagnostics with recovery loops in Step 8 — approaching the level-5 anchor. What keeps it at 4: Step 6's monitoring bullet points to a 'monitoring section in Critical Concepts' that does not exist (monitoring content lives in Template 10), a broken navigation checkpoint, and the migration workflow's verification step is delegated rather than spelled out.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), so everything — the full template catalog, the troubleshooting symptom catalog, and the migration guide — is inlined in one ~860-line SKILL.md. Section headers are clear and consistent, so it is navigable ('some structure'), but content that clearly belongs in separate files (Templates, Troubleshooting, Migration) is inline, matching the level-3 anchor rather than level 4's 'most content is appropriately placed'.

3 / 5

Total

14

/

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 description: third-person, concrete, and comprehensive on both capabilities and trigger phrases, with an explicit triggers clause covering natural user phrasings and synonyms. The only nit is the mild promotional filler '(Snowpipe Streaming high-performance architecture)', which adds little but costs almost nothing.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions — 'Set up, configure, and troubleshoot', 'fresh installations, connector property configuration for default pipe and user-defined pipe modes, server-side and client-side validation, JMX monitoring, migration from V3, and common error diagnosis' — with comprehensive coverage of the skill's scope. It matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' and is not one level below, where coverage would show minor gaps.

5 / 5

Completeness

It explicitly answers both what ('Set up, configure, and troubleshoot the Snowflake Kafka Connector V4... Covers fresh installations, ... migration from V3, and common error diagnosis') and when ('Triggers: kafka connector v4, kafka connector setup, ...'), which is the explicit trigger-guidance equivalent of a 'Use when...' clause. Not the level-4 anchor, since the 'when' is fully explicit with concrete trigger phrases rather than merely serviceable.

5 / 5

Trigger Term Quality

The trigger clause covers natural phrases users would actually say: 'kafka connector v4, kafka connector setup, kafka connector config, kafka connector troubleshoot, snowflake kafka connector, configure kafka connector, kafka connector help, kafka streaming connector' — including synonyms and phrasing variants. This fits the 'comprehensive coverage of natural terms including synonyms' anchor rather than the level-4 anchor, which expects a few natural terms missing.

5 / 5

Distinctiveness Conflict Risk

The description is pinned to a clear niche — the Snowflake Kafka Connector V4 and its Snowpipe Streaming architecture — with product-specific triggers, so overlap risk with other skills is minimal. Generic 'kafka connector' phrasing could superficially overlap a generic Kafka skill, but the consistent Snowflake/V4 qualifiers keep conflict risk minimal, matching the level-5 anchor.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (866 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
snowflakedb/snowpipe-streaming-sdk-examples
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.