> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rubixkube.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Skills Store

> Browse and enable system skills built by RubixKube, or create your own. Every skill is a reusable runbook the SRI Agent can run.

The Agent Skills Store is the catalogue of runbooks your SRI Agent can run. System skills are built and maintained by RubixKube. Custom skills live inside your workspace.

Every skill uses the [open Agent Skills format](/concepts/skills), the same format adopted by Cursor, Claude Code, and GitHub Copilot.

## Browse by category

<CardGroup cols={2}>
  <Card title="Triage" icon="stethoscope">
    Systematic health checks across an environment.
  </Card>

  <Card title="Investigation" icon="magnifying-glass">
    Focused deep-dives on a single signal or resource.
  </Card>

  <Card title="Automation" icon="gear">
    Recurring tasks: handoffs, post-deploy checks, cost reviews.
  </Card>

  <Card title="Bridge" icon="link">
    Skills that move information between tools (Linear, Notion, Slack).
  </Card>
</CardGroup>

## System skills available today

<AccordionGroup>
  <Accordion title="kubernetes-cluster-triage" icon="dharmachakra">
    **Category:** Triage. **Agent:** SRI Agent.

    Systematic health check of a Kubernetes cluster. Analyses infrastructure, identifies unhealthy resources, gathers diagnostics, returns a ranked list of attention points.

    **Allowed tools:** `fetch_infrastructure_snapshot`, `fetch_kubernetes_graph_snapshot`, `analyze_kubernetes_resources`, plus related read-only inspectors.
  </Accordion>

  <Accordion title="linear-tickets-to-notion" icon="list-check">
    **Category:** Bridge. **Agent:** SRI Agent.

    Fetches the current operator's assigned Linear issues and posts them into a new Notion page for a weekly review or handoff.

    **Allowed tools:** Linear and Notion MCP integrations.
  </Accordion>

  <Accordion title="research-devops-sre-infra" icon="book">
    **Category:** Investigation. **Agent:** SRI Agent.

    Web-search-backed research skill for DevOps, SRE, and infrastructure topics. Useful when an incident touches an unfamiliar technology.

    **Allowed tools:** Web search.
  </Accordion>
</AccordionGroup>

## Enable a system skill

<Steps titleSize="h3">
  <Step title="Open the Skills page">
    In the console, navigate to **Skills**. Filter by **System** to see the catalogue.
  </Step>

  <Step title="Review tool access">
    Click into the skill. The **Allowed tools** list shows exactly what the agent can call when the skill runs. Nothing outside this list is ever invoked.
  </Step>

  <Step title="Toggle enabled">
    Flip the switch. The SRI Agent now picks the skill up on matching prompts, and users can invoke it directly with `/skills skill-name`.
  </Step>
</Steps>

## Publish a custom skill

Every RubixKube workspace can publish its own tenant-scoped skills. Two paths:

<CardGroup cols={2}>
  <Card title="Console editor" icon="pen-to-square">
    Write YAML and instructions inline, test against live infrastructure, then save.
  </Card>

  <Card title="Upload a SKILL.md" icon="file-arrow-up">
    Bring a skill file written for Cursor, Claude Code, or Copilot. RubixKube validates against the open spec and imports.
  </Card>
</CardGroup>

See the full walkthrough in [How to add custom agent skills](/tutorials/add-custom-agent-skills).

## Store rules

* System skills are read-only. Clone one to adapt it for your workspace.
* Custom skills are scoped to a single workspace by default.
* Enterprise customers can share custom skills across workspaces in their organisation.

## Related guides

<CardGroup cols={2}>
  <Card title="Agent Skills concepts" icon="sparkles" href="/concepts/skills">
    What a skill is, how it is scored, where it runs.
  </Card>

  <Card title="How to add custom agent skills" icon="plus" href="/tutorials/add-custom-agent-skills">
    Step-by-step guide to writing and shipping your first skill.
  </Card>
</CardGroup>