KubeSphere DevOps ArgoCD

94TrustedInstructions only

GitOps deployment and ArgoCD management within the KubeSphere DevOps environment.

What it does

Adding this skill updates the assistant with deep knowledge of how to bridge GitOps workflows inside a KubeSphere cluster. It provides guidance on the distinction between direct ArgoCD administration and tenant-specific application management, ensuring your assistant understands the unique architectural flow between namespaces.

The assistant will be able to explain how KubeSphere controllers handle synchronization, bridge authentication through Dex, and manage resource placement. It is designed to bridge the gap between abstract GitOps concepts and the specific API endpoints and custom resources used by your installation.

When it earns its place

Reach for it when…

Use this when you are setting up continuous deployment pipelines, mapping repository credentials, or troubleshooting synchronization errors between your Git source and cluster state. It is effective for teams transitioning from manual deployments to multi-cluster GitOps patterns within a tenant-isolated KubeSphere architecture.

Look elsewhere when…

This skill is not suitable for generic Kubernetes administration or general ArgoCD configuration outside of a KubeSphere environment. It does not provide troubleshooting for your internal Git providers, nor does it replace the need for basic understanding of CI/CD pipeline design or container image registry management.

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.

  • How do I set up a GitOps application in my KubeSphere tenant namespace?
  • Why is my ArgoCD application showing a sync error in KubeSphere?
  • What are the differences between direct ArgoCD and KubeSphere GitOps?
  • How can I configure SSO authentication for ArgoCD using Dex?

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-devops-argocd ~/.claude/skills/kubesphere-devops-argocd

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-devops-argocd .claude/skills/kubesphere-devops-argocd

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