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

96%

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

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.

A strong, well-structured skill body: actionable commands, explicit validation feedback loops, and clean one-level-deep progressive disclosure with all references real. The only weakness is mild verbosity in the run/handoff section.

Suggestions

Tighten Build Step 6 by factoring the shared Local run steps out of the per-environment branches, so Confluent Cloud and WarpStream only list their deltas instead of repeating the full sequence.

Consider moving the long WarpStream override preamble into references/warpstream-optimization.md and keeping only the load-trigger pointer in SKILL.md to reduce upfront token cost.

The Invariant Checklist's 12 items could be trimmed by merging closely related defaults (e.g., serdes + schema parity) to preserve the same guidance in fewer tokens.

Dimension	Reasoning	Score
Conciseness	Mostly lean with no concept padding, but Build Step 6's repeated Local/Confluent Cloud/WarpStream run-and-handoff branches are verbose and could be tightened; fits 'efficient with minor instances of over-explanation' rather than the fully lean top anchor.	4 / 5
Actionability	Fully executable guidance throughout — concrete commands ('docker compose up -d', './gradlew run', 'gradle wrapper --gradle-version 8.12'), specific config keys, and exact success markers ('State transition from REBALANCING to RUNNING').	5 / 5
Workflow Clarity	Clearly sequenced Architect/Build/Debug modes with numbered steps and explicit validation checkpoints plus feedback loops (diagnose via debugging.md, fix, restart, re-verify) for the risky run/deploy operations.	5 / 5
Progressive Disclosure	Clear overview with prominent lazy-load guidance, well-signaled one-level-deep references, and every referenced file verified present in the bundle; navigation is easy and no nesting beyond one level.	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.

An exemplary description: concrete actions, comprehensive natural trigger terms, explicit what/when guidance, and clear negative boundaries that prevent mis-triggering. Every dimension lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Architect, build, and debug') plus specific sub-capabilities (interactive queries, joins/windows/aggregations, rebalancing, state stores, lag, deserialization errors), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (architect/build/debug Kafka Streams apps) and 'when' ('Use when user mentions...'), and adds negative trigger guidance for additional clarity.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms users would say — KStream, KTable, topology, TopologyTestDriver, StreamsBuilder, GlobalKTable — plus symptom phrases and synonyms like 'joins/windows/aggregations'.	5 / 5
Distinctiveness Conflict Risk	Clear Kafka Streams niche with explicit negative triggers ('Do NOT trigger for Flink, connectors, CDC, or plain producer/consumer') minimizing conflict risk.	5 / 5
	Total	20 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: confluentinc/agent-skills
Path: skills/kafka-streams-programming/SKILL.md
Commit: edec375

Reviewed: 12 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.