ops-investigate-alert

Official

Investigate alerts end-to-end with data.

Authorc0x12c
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Investigate monitoring alerts by collecting metrics, logs, traces, and recent code changes to identify root causes and actionable next steps.

Core Features & Use Cases

  • Verify Monitoring MCP Availability: detect available monitoring platforms (Datadog, Grafana, PagerDuty) and determine data sources.
  • Parse Input & Fetch Details: map alert identifiers or URLs to monitors, pull monitor configuration, current state, last trigger, and affected services.
  • Query Metrics & Analyze Logs: gather time-windowed metrics around the alert and search logs for errors, timeouts, or anomalies.
  • Check Traces & Infra (When Available): examine distributed traces for latency or error patterns and check pod status / deployments if Kubernetes data is accessible.
  • Compile Investigation Summary: present a structured report with metrics, logs, traces, infra observations, and root-cause hypothesis.

Quick Start

Run the alert investigation by collecting metrics, logs, traces, and recent code changes for the active alert and produce a structured report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ops-investigate-alert
Download link: https://github.com/c0x12c/ai-toolkit/archive/main.zip#ops-investigate-alert

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.