How do I install the Review Cluster skill?

Run npx skillmds@latest add hiai-gg/review-cluster in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Cluster safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Cluster?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Cluster free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Review Cluster?

HiAi-gg (@hiai-gg) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Cluster by hiai-gg — Agent Skill

Name: Review Cluster
Author: HiAi-gg

Review Cluster

Perform a read-only health review of a Kubernetes cluster or namespace: node status, workload state, resource pressure, events, and obvious misconfigurations. Use when asked for an overall cluster or namespace health assessment.

HiAi-gg Updated Sep 17, 2026

File contents

Review Kubernetes Cluster Health

Use this skill to produce a read-only health assessment of a cluster (or a single namespace).

Workflow

1. Nodes

kubectl get nodes -o wide
kubectl describe nodes | grep -A5 -E 'Conditions:|Allocated resources:' | head -60

Look for: NotReady nodes, MemoryPressure/DiskPressure, high allocated request/limit ratios, taints blocking workloads.

2. Workloads

kubectl get deploy,sts,ds -A -o wide | awk 'NR==1 || $4!=1 || $5!=$3'   # non-ready
kubectl get pods -A --field-selector=status.phase!=Running -o wide
kubectl get pods -A | grep -E 'CrashLoopBackOff|ImagePullBackOff|Pending|Error'

Focus on non-ready replicas and abnormal pod phases.

3. Events

kubectl get events -A --sort-by=.lastTimestamp | tail -40

Recent Warning events with repeated counts are the highest-signal items.

4. Resource pressure

kubectl top nodes
kubectl top pods -A | sort -k3 -h | tail -20   # CPU
kubectl top pods -A | sort -k4 -h | tail -20   # memory

(Requires metrics-server.) Note any pod nearing its limits.

5. Networking and storage

kubectl get svc,ingress -A | grep -E 'Pending|LoadBalancer'  # stuck LBs
kubectl get pvc -A | grep -v Bound                          # non-bound PVCs

6. Report

Give a scored summary: healthy/at-risk areas, the top issues with evidence (node condition, event, top line), and recommendations ranked by impact. Keep recommendations separated from observations.

Guardrails

Entirely read-only. No kubectl drain, cordon, delete, or scale.
kubectl top may fail if metrics-server is absent — say so rather than interpreting nothing as "no load".

---name: review-clusterdescription: Perform a read-only health review of a Kubernetes cluster or namespace: node status, workload state, resource pressure, events, and obvious misconfigurations. Use when asked for an overall cluster or namespace health assessment.---# Review Kubernetes Cluster HealthUse this skill to produce a read-only health assessment of a cluster (or asingle namespace).## Workflow### 1. Nodes```bashkubectl get nodes -o widekubectl describe nodes | grep -A5 -E 'Conditions:|Allocated resources:' | head -60```Look for: `NotReady` nodes, `MemoryPressure`/`DiskPressure`, high allocatedrequest/limit ratios, taints blocking workloads.### 2. Workloads```bashkubectl get deploy,sts,ds -A -o wide | awk 'NR==1 || $4!=1 || $5!=$3' # non-readykubectl get pods -A --field-selector=status.phase!=Running -o widekubectl get pods -A | grep -E 'CrashLoopBackOff|ImagePullBackOff|Pending|Error'```Focus on non-ready replicas and abnormal pod phases.### 3. Events```bashkubectl get events -A --sort-by=.lastTimestamp | tail -40```Recent `Warning` events with repeated counts are the highest-signal items.### 4. Resource pressure```bashkubectl top nodeskubectl top pods -A | sort -k3 -h | tail -20 # CPUkubectl top pods -A | sort -k4 -h | tail -20 # memory```(Requires metrics-server.) Note any pod nearing its limits.### 5. Networking and storage```bashkubectl get svc,ingress -A | grep -E 'Pending|LoadBalancer' # stuck LBskubectl get pvc -A | grep -v Bound # non-bound PVCs```### 6. ReportGive a scored summary: healthy/at-risk areas, the top issues with evidence(node condition, event, top line), and recommendations ranked by impact. Keeprecommendations separated from observations.## Guardrails- Entirely read-only. No `kubectl drain`, `cordon`, `delete`, or `scale`.- `kubectl top` may fail if metrics-server is absent — say so rather than interpreting nothing as "no load".

Frequently asked questions