RepoAI
Browse MCPs

KubeSphere Gateway API

94TrustedShips scripts

External traffic management using Traefik and the Kubernetes Gateway API standard.

What it does

Adding this skill integrates the modern Kubernetes Gateway API standard into your workflow. It enables the assistant to manage proxy lifecycles using Traefik across cluster, workspace, and project levels. By using the GatewayProxy custom resource, you can orchestrate traffic entry points while keeping configuration aligned with standard Kubernetes networking definitions.

Once installed, the assistant can handle setup, uninstallation, and troubleshooting for these proxy instances. It shifts the management focus from legacy ingress configurations to the more extensible Gateway API approach, allowing for precise control over how services are exposed based on tenant scoping.

When it earns its place

Reach for it when…

Apply this when your environment requires Traefik-based proxying that aligns with the official Kubernetes Gateway API specifications. It is ideal for multi-tenant setups where you need to isolate gateways by cluster, workspace, or namespace using native resource patterns.

Look elsewhere when…

Do not use this for systems relying on the older, ingress-nginx based Gateway CRD (gateway.kubesphere.io/v2alpha2). If your infrastructure is strictly tied to legacy ingress controllers or if you do not require the specific features of the Traefik-backed GatewayProxy CRD, a standard ingress approach is more appropriate.

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.

  • install a new Traefik gateway proxy for my project
  • check if the gateway proxy in this workspace is ready
  • what is the status of the current cluster gateway proxy
  • help me troubleshoot why my gateway proxy is not responding

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-gateway-api ~/.claude/skills/kubesphere-gateway-api

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-gateway-api .claude/skills/kubesphere-gateway-api

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

How skills and MCP servers differ →