kafka-streams-programming

Architect, build, and debug Kafka Streams apps (JVM-embedded stream processing). Use when user mentions KStream, KTable, topology, TopologyTestDriver, StreamsBuilder, interactive queries, GlobalKTable, joins/windows/aggregations, or debugging issues (rebalancing, state stores, lag, deserialization errors). Also use when user wants to optimize Kafka Streams for WarpStream or tune Kafka Streams client configuration for WarpStream. Do NOT trigger for Flink, connectors, CDC, or plain producer/consumer.

Quality

85%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-architected skill with excellent progressive disclosure and workflow clarity — the three-mode structure (Architect/Build/Debug) with clear routing, validation checkpoints, and honest credential-gated handoff procedures is strong. Its main weaknesses are moderate verbosity (especially the near-duplicate WarpStream/CC blocks in Build Step 6) and limited inline actionability — nearly all executable details are delegated to reference files, meaning the SKILL.md alone doesn't provide copy-paste-ready code. The invariant checklist is a strong addition that encodes non-negotiable defaults concisely.

Suggestions

Add 1-2 minimal inline code snippets (e.g., a basic StreamsBuilder topology or a config Properties block) so the skill body itself provides some executable guidance without requiring reference file reads.

Consolidate the WarpStream and Confluent Cloud blocks in Build Mode Step 6 into a shared 'remote cluster' flow with environment-specific callouts, reducing ~30 lines of near-duplicate text.

Dimension	Reasoning	Score
Conciseness	The skill is generally well-structured and avoids explaining basic Kafka concepts, but it's quite long (~250 lines) with some repetition (WarpStream overrides mentioned in the preamble and again in Build Mode Step 6, environment confirmation repeated multiple times). The lazy-load preamble and invariant checklist are efficient, but the Build Mode Step 6 (Run the App) is very verbose with near-duplicate blocks for CC and WarpStream.	2 / 3
Actionability	The skill provides concrete workflows, specific config property names, and exact commands (e.g., `gradle wrapper --gradle-version 8.12`, `docker compose up -d`), but lacks inline executable code examples — it delegates nearly all implementation details to reference files. The invariant checklist names specific classes and properties which is good, but the Build and Architect modes are procedural checklists rather than copy-paste-ready guidance. No actual topology code or config snippets are shown inline.	2 / 3
Workflow Clarity	Excellent multi-step workflows with clear sequencing across all three modes. Build Mode Step 6 includes explicit validation checkpoints (confirm RUNNING state within ~30s, diagnose via debugging reference if not), feedback loops (fix, restart, re-verify), and honest handling of credential-gated environments. Debug Mode has a clear symptom→category→reference routing table. The invariant checklist serves as a final validation gate.	3 / 3
Progressive Disclosure	The skill exemplifies progressive disclosure: the preamble explicitly instructs lazy-loading with concrete examples of when to read which file, the body references 11 specific reference files by path with section-level pointers (e.g., `references/debugging.md` § Startup Failures), and all references are one level deep. The SKILL.md serves as a clear routing overview without inlining reference content.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive trigger terms covering both positive and negative matches, clearly answers both what and when, and carves out a distinct niche by explicitly excluding related but different technologies. The negative trigger list is a particularly strong feature for disambiguation.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Architect, build, and debug Kafka Streams apps', mentions specific concepts like JVM-embedded stream processing, joins/windows/aggregations, interactive queries, state stores, and optimization for WarpStream.	3 / 3
Completeness	Clearly answers both 'what' (architect, build, debug Kafka Streams apps) and 'when' (explicit 'Use when' clause with detailed trigger terms, plus a 'Do NOT trigger' exclusion list). Both dimensions are thoroughly addressed.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: KStream, KTable, topology, TopologyTestDriver, StreamsBuilder, interactive queries, GlobalKTable, joins, windows, aggregations, rebalancing, state stores, lag, deserialization errors, WarpStream. Also includes negative triggers (Flink, connectors, CDC) to reduce false matches.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche (Kafka Streams specifically, not general Kafka). The explicit exclusion of Flink, connectors, CDC, and plain producer/consumer significantly reduces conflict risk with adjacent skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: confluentinc/agent-skills
Commit: 9095afc

Reviewed: 21 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.