RepoAI
Browse MCPs

KubeSphere Core

94TrustedShips scripts

API request routing and resource coordination for KubeSphere environments.

What it does

Installing this skill equips your assistant to act as a central bridge for your KubeSphere platform. It organizes how your assistant interacts with the underlying API layer, enabling it to manage multi-cluster connectivity, tenant workspaces, and extension resources with standardized path handling.

By including this, you allow your assistant to handle requests by identifying whether they belong to the broader platform API or a specific member cluster. It automates the technical routing logic required to query workspace-scoped data, reducing manual path construction and authentication overhead during your sessions.

When it earns its place

Reach for it when…

Use this when your assistant needs to query multi-cluster environments, manage tenant workspaces, or perform administrative tasks across a KubeSphere installation, particularly when you need to switch contexts between distinct member clusters dynamically.

Look elsewhere when…

Do not use this for managing raw, non-KubeSphere Kubernetes resources that exist outside the platform's API server. This skill is specifically for KubeSphere-aware operations and will not provide benefits for interacting with standalone manifests or basic kubectl commands.

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.

  • Connect to the member-1 cluster and list the namespaces
  • Show me the workspace templates available on the current KubeSphere instance
  • Route this API request through the KubeSphere server
  • Query the status of resources in the demo workspace

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/kubesphere-core ~/.claude/skills/kubesphere-core

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/kubesphere-core .claude/skills/kubesphere-core

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

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

How skills and MCP servers differ →