The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches installation manifests and scripts from official project repositories including the Argo Project on GitHub, the Istio project website, and the Linkerd installation service. These represent standard installation procedures for well-known and established open-source infrastructure tools.
[COMMAND_EXECUTION]: The skill provides numerous examples of shell commands and kubectl operations intended for cluster management, CLI installation (e.g., clusterctl), and resource debugging. These commands are consistent with the skill's primary purpose as a Kubernetes specialist.
[INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect injection by ingesting and processing untrusted external data.
Ingestion points: The skill reads external data through tools like kubectl logs and kubectl describe, as documented in references/troubleshooting.md and SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded instructions are present in the command examples.
Capability inventory: The skill utilizes extensive capabilities including shell command execution (kubectl, curl, bash) and file system operations.
Sanitization: No explicit sanitization or filtering of external container logs or event data is performed before displaying them to the user or agent context.

kubernetes-specialist