it-operations

Document a business process - flowcharts, RACI, and SOPs

Triage open Auvik alerts, rank by severity, and recommend dismissals for known noise

Scan Auvik interface statistics for saturated links and recurring congestion

Inventory devices for an Auvik tenant with type, manage status, and lifecycle breakdown

Audit a tenant's networks, interfaces, and saved configurations; flag drift and missing backups

Use this agent for Auvik alert-related questions - what's open, what matters, what to dismiss, what to escalate. Trigger for: triage alerts, what's alerting, open alerts, critical alerts Auvik, dismiss noise, alert storm, NOC queue Auvik, what's wrong right now. Examples: "Triage the overnight Auvik queue", "What's critical across all tenants right now?", "ACME has 40 open alerts - tell me which to actually look at", "Can I dismiss these flap alerts safely?"

Use this agent for Auvik utilization, saturation, and headroom questions - "is this link maxed out?", "what links need an upgrade?", "where is the bottleneck?". Trigger for: capacity planning, link utilization, saturated link, bandwidth headroom, network upgrade Auvik, p95 utilization, hotspot interfaces, bottleneck Auvik, WAN saturation, uplink utilization. Examples: "Which links at ACME are running hot?", "Capacity plan for the next quarter at tenant 12345", "Is the WAN saturated?", "Find me every interface above 70% p95 in the last 7 days"

Use this agent when an MSP needs a comprehensive device health audit across their NinjaOne-managed organization portfolio. Trigger for: device health check, fleet audit, offline device report, patch gap analysis, alert triage, backup status, organization health report, NinjaOne review, managed device sweep. Examples: "Give me a health report for all our NinjaOne-managed clients", "Which organizations have critical alerts right now?", "Show me all offline servers and devices with disk space issues"

Use this agent when the user is asking what's wrong with a tenant's network, investigating broad performance complaints, mapping topology, or doing multi-signal triage across devices, interfaces, alerts, and statistics in Auvik. Trigger for: investigate the network, what's wrong with <tenant>, the network is slow, find the bottleneck, topology audit, multi-signal triage, network health check, network performance Auvik. Examples: "Investigate ACME's network - they say it's slow", "Audit the topology for tenant 12345", "Something is off with the LA office network", "Pull a network health snapshot for ACME and tell me what to fix first"

Use this agent when an MSP needs dedicated patch compliance reporting across their NinjaOne-managed portfolio - not a general health check, but a focused analysis of OS patch levels, third-party application versions, missing critical patches, devices pending reboot, and patch policy exceptions. Trigger for: patch compliance report, patch status NinjaOne, missing patches NinjaOne, Windows update compliance, third-party patch report, QBR patch data, patch exceptions NinjaOne, patch policy review. Examples: "Generate a patch compliance report for all our clients for the QBR", "Which organizations have devices missing critical security patches?", "Show me all devices pending reboot after patching across every client"

Use this skill when working with Auvik alerts - severity tiers, status lifecycle, dismissal semantics, and the common alertName patterns that show up in MSP NOC queues.

Use this skill when working with the Auvik MCP tools - JSON:API envelope shape, basic-auth credential model, region routing, cursor-based pagination, rate-limit handling, and the v1 vs v2 device API distinction.

Use this skill when working with Auvik device records - identifying device types, interpreting manageStatus, reading lifecycle and warranty fields, and choosing between the v1 list endpoint and the detailed device endpoints.

Use this skill when working with Auvik network and interface entities - the network entity model, IP-range scoping, interface-to-device relationships, and admin vs oper status.

Plan and execute organizational or technical changes. Trigger with "we're changing", "rolling out", "migration plan", "how do we communicate this change", "change management plan", or when the user is planning a change that affects people, processes, or systems.

1 hook across 1 event