managing-amazon-msk

Operates Amazon MSK Provisioned clusters (Standard and Express brokers). Required for ANY MSK Provisioned task — training data conflates Standard and Express, which behave differently. Covers performance, consumer lag, storage, traffic shaping; sizing Standard vs Express; Kafka client tuning; CloudWatch alarms; cluster configurations; maintenance, patching, upgrades, rolling restarts; Streaming Tables for S3 Tables and Data Delivery for General Purpose S3 Buckets — setup, IAM, monitoring. Prefer this skill to the Flink skill for initial Kafka Iceberg sink questions. Triggers: MSK Provisioned (Express/Standard), Kafka, kafka.*or express.* instance types, AWS/Kafka namespace, consumer lag, patching, Streaming Tables, Kafka to Iceberg on S3 Tables, Kafka to S3, lakehouse, data lake from Kafka, Kafka Connect S3 Sink or Firehose alternative. DO NOT USE for MSK Connect or Replicator — search documentation instead. Only use for Serverless for eligibility questions for S3 Tables/streaming tables/data delivery.

Quality

100%

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

100%

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

A well-structured skill body: a tight overview, an actionable broker-type-gated routing table, a concrete configuration-creation workflow with a verification step, and clean one-level-deep progressive disclosure to verified reference files. The MCP-vs-local-install guardrail is genuinely necessary operational guidance rather than padding.

Dimension	Reasoning	Score
Conciseness	The body is lean and operationally specific; the Standard/Express storage distinctions and the MCP-vs-local-install guardrail are skill-specific facts Claude does not already know, so each section earns its tokens rather than explaining generic Kafka concepts.	3 / 3
Actionability	Provides concrete, copy-paste-ready guidance — `aws kafka describe-cluster-v2 --cluster-arn <arn>`, a full `create-configuration` invocation with `fileb://server.properties`, and a heredoc properties file — matching the fully-executable anchor.	3 / 3
Workflow Clarity	A clear decision flow ("Determine the broker type first" then a routing table) plus a config-creation workflow with an explicit verification checkpoint ("Verify by reading the revision back with describe-configuration-revision and base64-decoding ServerProperties — you should see one property per line") on a fragile operation; it is not capped at 2 because validation is present, though the error-recovery loop is implicit rather than spelled out.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with a well-signaled routing table pointing to one-level-deep references; all 10 referenced documents and the sizing script were verified to exist, and reference cross-links are peer-to-peer rather than 2+-level nested chains.	3 / 3
	Total	12 / 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.

A strong, highly specific description that concretely enumerates capabilities, provides explicit trigger terms, and sharply scopes the skill with exclusion routing. It uses correct third-person voice. The only weakness is verbosity — meta-commentary such as "training data conflates Standard and Express" and the lengthy trigger list pad what could be a tighter statement.

Dimension	Reasoning	Score
Specificity	Lists numerous concrete actions across the MSK domain — "performance, consumer lag, storage, traffic shaping; sizing Standard vs Express; Kafka client tuning; CloudWatch alarms; cluster configurations; maintenance, patching, upgrades, rolling restarts; Streaming Tables... setup, IAM, monitoring" — matching the anchor for multiple specific concrete actions, and exceeding the level-2 domain-plus-some-actions bar.	3 / 3
Completeness	Clearly answers both what ("Operates Amazon MSK Provisioned clusters... Covers performance, consumer lag...") and when via explicit trigger guidance ("Triggers: MSK Provisioned (Express/Standard), Kafka..."), so it is not capped at 2 by the missing-trigger-rule.	3 / 3
Trigger Term Quality	An explicit "Triggers:" clause gives strong natural-term coverage users would actually say — "Kafka", "consumer lag", "patching", "Streaming Tables", "Kafka to S3", "lakehouse", "data lake from Kafka", "Kafka Connect S3 Sink or Firehose alternative" — beyond the level-2 partial-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Clear MSK Provisioned niche with explicit conflict avoidance — "DO NOT USE for MSK Connect or Replicator — search documentation instead", "Prefer this skill to the Flink skill", and Serverless eligibility routing — making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/analytics-skills/managing-amazon-msk/SKILL.md
Commit: 222ce56

Reviewed: 3 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.