{"slug":"msk-operations","title":"msk-operations","summary":"Amazon MSK Provisioned operations, troubleshooting, and health","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-17T16:54:18.700875Z","repo":{"url":"https://github.com/aws/tools-for-devops-agent","stars":82,"forks":62,"license":"Apache-2.0","updatedAt":"2026-09-25T14:34:10Z"},"bodyHtml":"

MSK Operations — AWS DevOps Agent Skill

\n

An Amazon MSK Provisioned operations, troubleshooting, and health-assessment\nskill for AWS DevOps Agent.\nCovers Standard and Express brokers and both proactive operational reviews and\nad-hoc incident response (performance, consumer lag, storage, maintenance,\nclient tuning).

\n
\n

⚠️ Non-production disclaimer. This skill is sample code, not intended for\nproduction use without additional review and testing. Users should validate in\na non-production environment first.

\n
\n

Purpose

\n

Give AWS DevOps Agent the domain knowledge to answer MSK questions accurately\nwithout falling back on training data (which routinely conflates Standard and\nExpress broker behavior). The skill activates in two shapes:

\n
    \n
  1. Operational review — assess an MSK cluster's health against best\npractices and produce a prioritized findings report.
    2. \n
  2. Ad-hoc troubleshooting — investigate a specific MSK symptom (high CPU,\nconsumer lag, disk full, TrafficShaping, unexpected broker restart, etc.)\nand recommend the correct next action.
    3. \n
\n

Key Capabilities

\n\n

Prerequisites

\n

IAM permissions

\n

The AWS DevOps Agent's primary cloud-source role needs read access to MSK and\nCloudWatch. All calls except kafka:GetBootstrapBrokers are covered by\nAIDevOpsAgentAccessPolicy. kafka:GetBootstrapBrokers is granted by the\nopt-in EnableMskOperations parameter (default true) in\ncloudformation/devops-agent-skill-policies.yaml.\nThe full set of actions the skill uses in practice:

\n
kafka:DescribeClusterV2\nkafka:ListClustersV2\nkafka:ListNodes\nkafka:GetBootstrapBrokers\nkafka:ListClusterOperationsV2\nkafka:DescribeConfigurationRevision\nkafka:ListConfigurations\ncloudwatch:GetMetricData\ncloudwatch:GetMetricStatistics\ncloudwatch:ListMetrics\ncloudwatch:DescribeAlarms\nlogs:DescribeLogGroups\nlogs:FilterLogEvents\n
\n

Write actions (UpdateBrokerStorage, CreateConfiguration,\nPutMetricAlarm, etc.) are only recommended in the skill output — the operator\nis expected to run them after review.

\n

Cluster access

\n\n

Limitations

\n\n

Agent Types

\n

This skill is intended for the following agent types (selected in the Operator\nWeb App at upload time):

\n\n

Select Generic instead if you want the skill available to all agent types.

\n

Uploading to AWS DevOps Agent

\n
\n

Reference: Uploading a skill

\n
\n

1. Package the skill

\n

From the skills/ directory in this repo:

\n
cd skills\nzip -r msk-operations.zip msk-operations/ -i '*.md' '*.txt' '*.json' '*.yaml' '*.yml' '*.xml' '*.csv' '*.tsv' '*.html' '*.htm' '*.png' '*.jpg' '*.jpeg' '*.gif' '*.svg' '*.webp' '*.pdf' -x '*/.claude/*' '*/scripts/*' '*/README.md' '*/.skilleval.yaml' '*/.skilleval.yml' '*/CHANGELOG.md' '*/evals/*'\n
\n

The resulting msk-operations.zip contains:

\n
msk-operations/\n├── SKILL.md\n└── references/\n    ├── troubleshoot-performance.md\n    ├── troubleshoot-consumer-lag.md\n    ├── manage-storage.md\n    ├── monitor-and-alarm.md\n    ├── maintenance-operations.md\n    └── configure-clients.md\n
\n

Constraints (enforced at upload time):

\n\n

2. Upload via the Operator Web App

\n
    \n
  1. Navigate to the Skills page in your Agent Space Operator Web App.
    2. \n
  2. Click Add skill → Upload skill.
    3. \n
  3. Drag and drop msk-operations.zip (or browse to it).
    4. \n
  4. Select agent types: Chat tasks and Evaluation (or leave Generic\nto make it available to all agent types).
    5. \n
  5. Review the validation results.
    6. \n
  6. Click Upload.
    7. \n
\n

How to Use This Skill

\n

In DevOps Agent Chat, use natural language. You do NOT need to mention the\nskill name — the agent activates it based on the MSK / Kafka triggers in the\nskill description.

\n

Ad-hoc troubleshooting prompts

\n\n

Operational-review prompts

\n\n

Client tuning prompts

\n\n

Skill Contents

\n
msk-operations/\n├── SKILL.md\n├── README.md\n├── CHANGELOG.md\n├── .skilleval.yaml\n├── evals/\n│   ├── evals.json\n│   └── eval_queries.json\n└── references/\n    ├── troubleshoot-performance.md\n    ├── troubleshoot-consumer-lag.md\n    ├── manage-storage.md\n    ├── monitor-and-alarm.md\n    ├── maintenance-operations.md\n    └── configure-clients.md\n
\n

README.md, CHANGELOG.md, .skilleval.yaml, and evals/ are for repo\nmaintenance and are not required at the cluster — the zip command above\nexcludes them from the upload artifact.

\n","files":[{"path":"CHANGELOG.md","sizeBytes":1460,"isText":true},{"path":"evals/benchmark.json","sizeBytes":27255,"isText":true},{"path":"evals/eval_queries.json","sizeBytes":1059,"isText":true},{"path":"evals/evals.json","sizeBytes":3178,"isText":true},{"path":"evals/report.json","sizeBytes":1604,"isText":true},{"path":"evals/trigger_report.json","sizeBytes":3454,"isText":true},{"path":"README.md","sizeBytes":8194,"isText":true},{"path":"references/configure-clients.md","sizeBytes":6873,"isText":true},{"path":"references/maintenance-operations.md","sizeBytes":12558,"isText":true},{"path":"references/manage-storage.md","sizeBytes":7250,"isText":true},{"path":"references/monitor-and-alarm.md","sizeBytes":13630,"isText":true},{"path":"references/troubleshoot-consumer-lag.md","sizeBytes":11390,"isText":true},{"path":"references/troubleshoot-performance.md","sizeBytes":9304,"isText":true},{"path":".skilleval.yaml","sizeBytes":77,"isText":true},{"path":"SKILL.md","sizeBytes":26682,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-17T16:54:53.193899Z","sha256":"9AD042D753B1B4BDF4C897ABAA032CFAECB873E465A7AF3A10108656BF974C85","sizeBytes":47977},"review":null,"source":{"repositoryUrl":"https://github.com/aws/tools-for-devops-agent","path":"skills/msk-operations","license":"Apache-2.0","commit":"a9ca636abac7bde16132ce9508586143753db97a","subtreeSha":"1C73E190F4C9B4FF2408460401D8159E729DCA719B1F5AEA5330C3821496C755","lastSyncedAt":"2026-09-25T23:11:37.941909Z"},"reviewedAt":"2026-09-17T16:56:15.15097Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/aws/tools-for-devops-agent/tree/main/skills/msk-operations"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install aws-tools-for-devops-agent@llmmart"},{"target":"git","command":"git clone https://github.com/aws/tools-for-devops-agent.git"}]}