Tessl • The management layer for AI agent skills

SkillPublic

kafka-stream-processing

Complete guide for Apache Kafka stream processing including producers, consumers, Kafka Streams, connectors, schema registry, and production deployment

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/luxor-data-engineering/skills/kafka-stream-processing/SKILL.md

Quality

Content

46%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 comprehensive but bloated monolith: strong executable examples and configuration references are buried under conceptual explanations Claude already knows and pasted documentation excerpts. Without any bundle files, progressive disclosure is absent, and there is no task-oriented workflow with validation checkpoints.

Suggestions

Split the body into reference files (e.g., references/producer-config.md, references/streams.md, references/metrics.md, references/deployment.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Delete or drastically trim the conceptual explanations and verbatim documentation excerpts (the raw HTML section, prose inside java code fences, the duplicated topology-naming table) — Claude already knows Kafka's architecture.

Add at least one end-to-end workflow with validation checkpoints, e.g., build topology → unit-test with TopologyTestDriver → verify consumer lag and output topic before treating a deployment as successful.

Dimension	Reasoning	Score
Conciseness	The ~1370-line body extensively explains concepts Claude already knows (Kafka architecture, 'Topics are logical channels for data streams', 'Partitions: Ordered, immutable sequences') and pastes large documentation excerpts verbatim, including a raw HTML block, prose inside java code fences, and a duplicated topology-naming table. It is not a 1 because the config tables and code examples do carry real information.	2 / 5
Actionability	Contains substantial executable material: complete Java producer/consumer examples, CLI commands (kafka-topics.sh, kafka-consumer-groups.sh), properties configurations, and JSON connector configs. Minor gaps keep it below 5 — some blocks are pseudocode or doc stubs (the 'ProducerClient.publish' APIDOC, 'kstream.repartition(...)' fragments, and patterns written as comments).	4 / 5
Workflow Clarity	Sequences exist in places (rolling upgrade steps, troubleshooting issue→action lists, offset-commit strategy ordering), but the skill is a reference dump with no coherent task workflow and no validation checkpoints or feedback loops (e.g., verify a deployment, test a topology before promoting). It is above 2 because troubleshooting sections do provide implicit checkpoint guidance.	3 / 5
Progressive Disclosure	There are no bundle files at all; the entire skill is one monolithic SKILL.md with full metrics tables, Kafka Streams documentation excerpts, and API reference material inlined — content that clearly belongs in separate reference files. It is not 1 because the document does have a well-formed section hierarchy, but with zero reference files and everything inline it cannot reach 3.	2 / 5
	Total	11 / 20 Passed

Description

66%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 solid, domain-specific description with good keyword coverage and clear capability enumeration. Its main weaknesses are the complete absence of a 'when to use' trigger clause and reliance on topic nouns rather than concrete action verbs, plus a few missing natural synonyms.

Suggestions

Add an explicit trigger clause, e.g., 'Use when working with Apache Kafka, building event-driven services, processing real-time data streams, or when the user mentions producers, consumers, Kafka Streams, or Kafka Connect.'

Lead with action verbs instead of a noun list — e.g., 'Build, configure, and deploy Apache Kafka applications: producers, consumers, Kafka Streams, Connect connectors, schema registry, and production deployment.'

Include common synonyms such as 'event streaming', 'pub/sub', 'message broker', and 'real-time data pipeline' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and six concrete capability areas ("producers, consumers, Kafka Streams, connectors, schema registry, and production deployment"), giving specific coverage with only minor gaps. It falls short of a 5 because it lists topic areas rather than concrete actions (e.g., 'build', 'configure', 'deploy'), and is above 3 because coverage is broad and specific rather than just 1-2 actions.	4 / 5
Completeness	The 'what' is clear (a complete guide to Kafka stream processing covering six areas), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is specific and comprehensive, not vague.	3 / 5
Trigger Term Quality	Includes natural terms users would say such as 'Kafka', 'stream processing', 'producers', 'consumers', 'connectors', and 'schema registry'. A few natural terms are missing (e.g., 'event streaming', 'pub/sub', 'message broker', 'real-time data'), keeping it below 5 but above the partial-keyword anchors at 3.	4 / 5
Distinctiveness Conflict Risk	Kafka-specific terms ('Kafka Streams', 'schema registry', 'connectors') give it a clear niche with minimal conflict risk. It is not a 5 because 'stream processing', 'connectors', and 'production deployment' could overlap with adjacent event-driven or data-pipeline skills; it is well above the generic anchors at 3.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1375 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: manutej/luxor-claude-marketplace
Path: plugins/luxor-data-engineering/skills/kafka-stream-processing/SKILL.md
Revision: 1861cc9

Reviewed: 26 days ago

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.

kafka-stream-processing

Table of Contents

Is this your skill?