k8s-diagnostics — Claude Code skill: what it does, how to install
k8s-diagnostics — a skill that has the agent pull pod and node metrics, run cluster health checks and diff two namespaces using kubectl-mcp-server tools.
MIT-0 1 installs ★ 976 updated 2026-10-22
npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a claude-codeWhat k8s-diagnostics does
The skill maps 10 tools for the agent: health_check, kubectl_top, get_nodes_summary, compare_namespaces, kubectl_get, get_api_resources, kubeconfig_view, list_contexts, plus kubectl_logs and kubectl_describe when something breaks. It fires when you mention metrics, a health check, capacity or the difference between two environments.
Three workflows cover most of it. A cluster overview runs the health check, the node summary and the events list. A pre-release pass reads kubectl_top on production, pulls the node summary and diffs staging against production deployments. After an incident the agent collects events, logs from the previous container and a describe of the pod.
Start kubectl-mcp-server with the diagnostics and multicluster toolsets: --toolsets default,diagnostics,multicluster or MCP_TOOLSETS=default,diagnostics,multicluster. Metrics need metrics-server running in the cluster, and without it kubectl_top returns nothing useful.
What it helps with
- read CPU and memory numbers for pods and nodes
- run a health check before a rollout
- diff deployments between staging and production
- gather events and previous-container logs after a crash
- list CRDs and discovered API resources
Example prompts for the agent
- Check cluster health and show the top pods by memory in
production. - Compare
stagingandproductiondeployments before the release. - A pod just crashed — pull events, logs from the previous container and
kubectl_describe.
How to install k8s-diagnostics
1Skills CLI (Vercel)
npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a claude-code2Manually: put the files in place
~/.claude/skills/k8s-diagnostics/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/k8s-diagnostics/
1Skills CLI (Vercel)
npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a codex2Manually: put the files in place
.agents/skills/k8s-diagnostics/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a cursor2Manually: put the files in place
.cursor/skills/k8s-diagnostics/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/kubectl-mcp-server kubernetes-skills/claude/k8s-diagnostics2Manually: put the files in place
.github/skills/k8s-diagnostics/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/kubectl-mcp-server --path kubernetes-skills/claude/k8s-diagnosticsManually: put the files in place
.devin/skills/k8s-diagnostics/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about k8s-diagnostics
How do I install k8s-diagnostics in Claude Code?
Run npx skills add rohitg00/kubectl-mcp-server --skill k8s-diagnostics -a claude-code; the skill lands in ~/.claude/skills/k8s-diagnostics/SKILL.md.
What does k8s-diagnostics do?
It tells the agent which kubectl-mcp-server tools to call for metrics, cluster health, namespace comparisons and post-incident data collection.
What has to be running for the skill to work?
A kubectl-mcp-server started with the diagnostics and multicluster toolsets, and metrics-server in the cluster for anything metric-related.
Source text
SKILL.md · MIT-0
---
name: k8s-diagnostics
description: Kubernetes diagnostics for metrics, health checks, resource comparisons, and cluster analysis. Use when analyzing cluster health, comparing environments, or gathering diagnostic data.
license: MIT-0
metadata:
author: rohitg00
version: "2.0.0"
tools: 10
category: observability
---
# Kubernetes Diagnostics
Analyze cluster health and compare resources using kubectl-mcp-server's diagnostic tools.
> Requires the `diagnostics`, `multicluster` toolsets: start kubectl-mcp-server with `--toolsets default,diagnostics,multicluster` (or `MCP_TOOLSETS=default,diagnostics,multicluster`).
## When to Apply
Use this skill when:
- User mentions: "metrics", "health check", "compare", "analysis", "capacity"
- Operations: cluster health assessment, environment comparison, resource analysis
- Keywords: "how much", "usage", "difference between", "capacity planning"
## Priority Rules
| Priority | Rule | Impact | Tools |
|----------|------|--------|-------|
| 1 | Check metrics-server before using metrics | CRITICAL | `kubectl_top` |
| 2 | Run health check before deployments | HIGH | `health_check` |
| 3 | Compare staging vs prod before release | MEDIUM | `compare_namespaces` |
| 4 | Document baseline metrics | LOW | `get_nodes_summary` |
## Quick Reference
| Task | Tool | Example |
|------|------|---------|
| Cluster health | `health_check` | `health_check()` |
| Pod metrics | `kubectl_top` | `kubectl_top(namespace)` |
| Node summary | `get_nodes_summary` | `get_nodes_summary()` |
| Compare envs | `compare_namespaces` | `compare_namespaces(ns1, ns2, type)` |
| List CRDs | `kubectl_get` | `kubectl_get(resource_type="crds")` |
## Resource Metrics
```python
kubectl_top(namespace="default")
kubectl_top(resource="nodes")
kubectl_top(resource="pods", namespace="default", sort_by="cpu")
kubectl_top(resource="pods", namespace="default", sort_by="memory")
```
## Cluster Health Check
```python
health_check()
health_check()
```
## Compare Environments
```python
compare_namespaces(
namespace1="staging",
namespace2="production",
resource_type="deployment"
)
kubectl_get(resource_type="deployments", namespace="default", context="staging-cluster")
kubectl_get(resource_type="deployments", namespace="default", context="prod-cluster")
```
## API Discovery
```python
get_api_resources()
kubectl_get(resource_type="crds", name="certificates.cert-manager.io")
kubectl_get(resource_type="crds")
```
## Resource Analysis
```python
get_nodes_summary()
kubeconfig_view()
list_contexts()
```
## Diagnostic Workflows
### Cluster Overview
```python
health_check()
get_nodes_summary()
kubectl_get(resource_type="events", namespace="")
kubectl_get(resource_type="crds")
```
### Pre-deployment Check
```python
kubectl_top(namespace="production")
get_nodes_summary()
compare_namespaces(namespace1="staging", namespace2="prod", resource_type="deployment")
```
### Post-incident Analysis
```python
kubectl_get(resource_type="events", namespace)
kubectl_logs(name, namespace, previous=True)
kubectl_top(namespace)
kubectl_describe(name)
```
## Related Skills
- [k8s-troubleshoot](../k8s-troubleshoot/SKILL.md) - Debug issues
- [k8s-cost](../k8s-cost/SKILL.md) - Cost analysis
- [k8s-incident](../k8s-incident/SKILL.md) - Incident response
© rohitg00 · MIT-0 · rohitg00/kubectl-mcp-server