RepoAI
Browse MCPs

Kubeeye

94TrustedShips scripts

Automated cluster diagnostics for KubeSphere environments via custom inspection rules.

What it does

Kubeeye acts as a diagnostic engine for Kubernetes clusters running on KubeSphere, transforming your assistant into an expert on cluster health. By coordinating with custom resource definitions, it enables the automation of complex checks ranging from kernel parameters to systemd status, ensuring consistent environment monitoring.

Installing this skill allows your assistant to manage the entire lifecycle of cluster audits. It interprets requests to define new inspection criteria, schedule routine scans, and parse the resulting data to help you identify configuration drift or performance bottlenecks.

When it earns its place

Reach for it when…

Apply this skill when managing cluster health checks within a KubeSphere environment. It is ideal for defining OPA policies, PromQL queries, or file integrity benchmarks and for automating periodic health scans using InspectPlan objects.

Look elsewhere when…

Do not use this for general Kubernetes troubleshooting that does not involve the Kubeeye framework. If you need to view raw logs from a single pod or debug a container runtime issue manually, standard kubectl commands or native KubeSphere dashboards are more direct and efficient.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • set up a new cluster inspection plan
  • how do I create an InspectRule for my cluster
  • show me the latest inspection results
  • create a scheduled scan for my Kubernetes environment

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch master https://github.com/kubesphere/kubesphere.git /tmp/kubesphere
mkdir -p ~/.claude/skills
cp -r /tmp/kubesphere/skills/kubeeye ~/.claude/skills/kubeeye

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/kubesphere/skills/kubeeye .claude/skills/kubeeye

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

Kubeeye changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →