What problem does it solve? When production incidents occur, teams often lack documented troubleshooting procedures, forcing engineers to improvise diagnosis and remediation steps under pressure. This Skill creates standardized, actionable runbooks for specific failure scenarios so on-call engineers can resolve issues faster. ## Core Features & Use Cases - Structured Runbook Generation: Produces runbooks with overview, prerequisites, symptoms, diagnosis, remediation, escalation, and prevention sections, pre-filled with real kubectl and Azure CLI commands. - Multi-Product Support: Covers Trigent products including Emergency Management, Training Platform, Visitor Management, CPOMS StudentSafe/StaffSafe, SmartPass, and SchoolPass, with product-specific namespaces and resource names resolved from the sre-kb GitLab group. - Confluence Publishing: Creates or updates runbook pages directly in the MI Confluence space under the Runbooks folder, checking for existing pages first. - Use Case: An SRE notices push notifications failing in Emergency Management and runs the skill with the scenario, receiving a complete runbook with ANH diagnosis commands, remediation options, and escalation contacts published to Confluence. ## Quick Start Ask the assistant to create a runbook for a specific product and failure scenario, for example: generate a runbook for em push notifications failing.
