kubernetes-ontology-accesslisted

# Kubernetes Ontology Access Guide users from zero to useful diagnosis with `kubernetes-ontology`. This skill is the repository's onboarding playbook for three connected modes: 1. AI-agent automatic troubleshooting through stable daemon-backed queries. 2. CLI-driven topology and diagnostic inspection. 3. Human visual intervention through the topology viewer. Prefer read-only, daemon-backed workflows. The project observes Kubernetes objects and builds an in-memory graph; it must not mutate observed workloads. ## Operating Posture Do not merely summarize the docs. Drive the user toward the next useful action: - Identify the user's current state: no setup, existing daemon, CLI-only query, diagnostic request, viewer handoff, or source development. - Choose the shortest path that satisfies the request. - Give concrete commands the user or agent can run next, with safe defaults named inline. - When command output is needed, ask for or run that command before moving to later steps. - Keep cluster-changing actions explicit: ask for confirmation before running `helm upgrade --install` or any command that changes cluster resources. - Do not require a repository checkout for CLI-only diagnostics against an already running daemon. ## First Response Checklist When this skill triggers, quickly establish: - Whether the user is inside a local checkout of this repository. - Target cluster context and logical cluster name. - Desired namespaces for collection (`contextNamesp