finops-cloudwatch
Reviews CloudWatch log retention policies and potential deletion candidates for cost optimization.
Install
mkdir -p .claude/skills/finops-cloudwatch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14451" && unzip -o skill.zip -d .claude/skills/finops-cloudwatch && rm skill.zipInstalls to .claude/skills/finops-cloudwatch
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review CloudWatch Logs retention and deletion-candidate findings.Key capabilities
- →Confirm environment, ingestion history, retention, and stored-bytes facts.
- →Check audit, security, legal-hold, incident-response, and replay requirements.
- →Reject deletion language when ownership or recent-event evidence is missing.
- →Explain whether candidate changes retention or requests more evidence.
How it works
This skill reviews CloudWatch Logs retention and deletion-candidate findings against a checklist, confirming facts and checking various requirements, then writes the decisions and rationale to a JSON file.
Inputs & outputs
When to use finops-cloudwatch
- →Review log retention policies
- →Audit cloud storage costs
- →Check legal-hold compliance
About this skill
CloudWatch Logs Review
Review-only authority: LangGraph owns detection and calculations. Claude must not rerun rule arithmetic.
Review Checklist
- Confirm environment, ingestion history, retention, and stored-bytes facts.
- Check audit, security, legal-hold, incident-response, and replay requirements.
- Reject deletion language when ownership or recent-event evidence is missing.
- Explain whether the candidate changes retention or only requests more evidence.
Output Contract
Write each finding decision and rationale to result/claude_review.json. Do not change machine savings or remediation candidates.
When not to use it
- →When the user needs to rerun rule arithmetic for detection and calculations.
- →When the user wants to trigger automated deletions based on findings.
Limitations
- →The skill has review-only authority.
- →It must not rerun rule arithmetic.
- →It does not change machine savings or remediation candidates.
How it compares
This skill provides a structured review and rationale for CloudWatch Logs retention findings, focusing on compliance and evidence, rather than directly modifying retention policies or performing calculations.
Compared to similar skills
finops-cloudwatch side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| finops-cloudwatch (this skill) | 0 | 1mo | No flags | Intermediate |
| mlops-engineer | 3 | 4mo | No flags | Advanced |
| genkit-infra-expert | 1 | 29d | Review | Advanced |
| cost-optimization | 1 | 5mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
mlops-engineer
sickn33
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
genkit-infra-expert
jeremylongshore
Execute use when deploying Genkit applications to production with Terraform. Trigger with phrases like "deploy genkit terraform", "provision genkit infrastructure", "firebase functions terraform", "cloud run deployment", or "genkit production infrastructure". Provisions Firebase Functions, Cloud Run services, GKE clusters, monitoring dashboards, and CI/CD for AI workflows.
cost-optimization
wshobson
Optimize cloud costs through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
cloudwatch
itsmostafa
AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.
checking-infrastructure-compliance
jeremylongshore
Execute use when you need to work with compliance checking. This skill provides compliance monitoring and validation with comprehensive guidance and automation. Trigger with phrases like "check compliance", "validate policies", or "audit compliance".
huawei-event-driven-architecture-review
Raishin
Review Huawei Cloud event-driven architecture designs — DMS Kafka dead-letter configuration, ROMA Connect integration flow capacity, FunctionGraph event trigger idempotency, SMN delivery retry policy, consumer group lag monitoring, cross-region event replication, and retry storm prevention.