parsec

Triage and diagnose an Icinga2 monitoring alert by correlating live host/service state with the check-script source and Icinga GitOps config from GitHub, then produce a root cause and an action plan. Use when someone reports a monitoring alert, a host or service is DOWN / CRITICAL / WARNING / UNKNOWN, or asks why an Icinga check is failing.

Triage a failed Ansible Automation Platform 2 (AAP2) controller job — find the failing task, extract the error from the job output and Splunk logs, and identify the root cause with a recommended fix. Use when an AAP2 job, workflow, or Babylon deployment fails and someone needs to know why.

Detect abusive or compromised sandbox accounts using Parsec's abuse indicators — GPU and oversized instances, suspicious instance names, high-volume external users, and disposable-email signups. Use when triaging a suspected crypto-mining, compromised-credential, or quota-abuse case.

Investigate an unexpected cloud cost spike across AWS, Azure, and GCP — pinpoint the driving account, service, and resource, then produce a cost breakdown with concrete remediation options. Use when someone reports a budget overrun, a sudden bill increase, or asks why costs went up.

This one has malformed YAML in the frontmatter.

A skill with an unknown key under the parsec block — should warn, not fail.

A minimal valid skill that does the bare minimum to load successfully.

A skill that uses the Parsec extension block to declare version, domain, and MCP dependencies. Use when testing the parsec extension parser.