RepoAI
Browse MCPs

Vector

94TrustedInstructions only

Data pipeline configuration for observability within KubeSphere environments.

What it does

This skill assists in deploying and managing the observability data pipeline within KubeSphere. It guides the assistant through the specific sequence required to prepare, validate, and finalize the installation of this core infrastructure component.

By installing this skill, your assistant gains the logic to map required credentials and cluster targets to the necessary configuration templates. It ensures that the deployment plan strictly adheres to the schema requirements of the platform, reducing the risk of syntax errors during setup.

When it earns its place

Reach for it when…

Use this when you are ready to set up or update the pipeline responsible for routing logs, events, and audit data to an OpenSearch instance. It is the primary tool for verifying available clusters, identifying the latest software versions, and generating the correct manifest for the installation.

Look elsewhere when…

Do not use this for general data analysis or for configuring the downstream observability tools like OpenSearch itself. This skill is strictly for the installation and initial connection phase of the pipeline agent; it does not provide diagnostics or troubleshooting for data flow issues after the system is running.

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.

  • help me install the vector extension in my cluster
  • how do I connect vector to my opensearch instance
  • configure the observability pipeline for k8s
  • what version of the vector extension should I use

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/vector ~/.claude/skills/vector

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/vector .claude/skills/vector

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

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

How skills and MCP servers differ →