incident-triaging

Classifies software incidents P0-P3 from error logs and outage reports into structured Triage Blocks.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/wizeline/sdlc-agents --skill incident-triaging
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: incident-triaging
Source: https://github.com/wizeline/sdlc-agents/tree/main/aicores/incident-resolution-agent/skills/incident-triaging
Command: npx skills add https://github.com/wizeline/sdlc-agents --skill incident-triaging

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the initial response to software incidents by quickly assessing their severity and gathering essential context, reducing ambiguity and accelerating the path to resolution.

Core Features & Use Cases

  • Automated Severity Classification: Assigns P0-P3 severity levels based on predefined criteria.
  • Context Gathering: Extracts key information like stage, symptom, scope, and system context from initial reports.
  • Use Case: When an alert fires for a production outage, this skill immediately classifies it as P0, identifies the affected service, and prepares a concise summary for the on-call engineer to begin root cause analysis.

Quick Start

Use the incident-triaging skill to classify the provided error log and determine its severity.

Frequently Asked Questions about incident-triaging

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I classify incident severity from error logs and stack traces?

Classify incident severity by analyzing stack traces, error logs, and outage reports to assign P0–P3 levels. The tool extracts stage, symptom, scope, and system context to produce a structured Triage Block detailing blast radius and SLA risk.

What is the difference between P0 and P3 severity in incident triage?

P0 severity indicates a critical production outage requiring immediate response, while P3 represents minor issues. The classification mechanism evaluates blast radius and SLA risk from initial reports to differentiate severity levels for the on-call engineer.

Can I use this for automated incident intake across all SDLC stages?

Yes, automated incident intake triggers on any signal indicating a system malfunction across all SDLC stages. It immediately classifies the alert, identifies affected services, and prepares a concise summary for root cause analysis.

What's the best way to prepare a structured triage block for an on-call engineer?

Produce a structured triage block by feeding error logs and outage reports into the classification process. It outputs a concise summary detailing severity, blast radius, SLA risk, and minimum context required to begin root cause analysis.

When do I need to evaluate SLA risk during incident management?

Evaluate SLA risk during incident management whenever a system malfunction alert fires. The severity classification process analyzes the blast radius and outage scope to determine potential SLA breaches and prioritize the response accordingly.

What context is needed for root cause analysis after severity classification?

Root cause analysis requires the minimum context gathered during incident intake, including stage, symptom, scope, and system context. The classification mechanism extracts this information to accelerate the path to resolution.