incident-commander

Run incident response workflows for outages, severity assessment, and status updates.

2|1|Updated May 17, 2026
One-click install
npx skills add https://github.com/rakibulism/agent-skills-os --skill incident-commander-rakibulism
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: incident-commander
Source: https://github.com/rakibulism/agent-skills-os/tree/main/skills/incident-commander
Command: npx skills add https://github.com/rakibulism/agent-skills-os --skill incident-commander-rakibulism

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you respond to production incidents without losing focus, by guiding you through triage, severity assessment, stakeholder communication, and postmortem writing in the right order.

Core Features & Use Cases

  • Incident Triage: Assess impact quickly and classify severity based on users affected, data risk, revenue impact, and workaround availability.
  • Status Communications: Produce clear, non-technical updates that explain what is broken, who is affected, what action is underway, and when the next update will arrive.
  • Blameless Postmortems: Turn a resolved incident into a factual timeline, root-cause analysis, impact summary, and actionable follow-ups.

Quick Start

Use the incident-commander skill to triage this outage: our checkout API is returning 500 errors for most users, and draft the next status update.

Frequently Asked Questions about incident-commander

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

FAQPage Schema
How do I assess incident severity during a production outage?

Incident severity assessment requires evaluating users affected, data risk, revenue impact, and workaround availability. This Skill guides you through classifying outages and major degradations to establish a clear severity rating for structured response prioritization.

How do I write non-technical status updates for a production incident?

Incident status updates should explain what is broken, who is affected, what mitigation action is underway, and when the next update will arrive. This Skill generates clear, non-technical stakeholder communications during active alert-driven response scenarios.

What is a blameless postmortem and how do I write one after an outage?

A blameless postmortem turns a resolved incident into a factual, timestamped timeline, root-cause analysis, impact summary, and actionable follow-ups with assigned owners. This Skill structures the postmortem process to focus on systemic factors rather than individual blame.

Can I use this for triage when my checkout API is returning 500 errors?

Yes, this Skill triages production outages like API 500 errors by applying structured impact assessment to determine severity, draft immediate status updates, and coordinate mitigation efforts with clear communication.

What is the best way to structure an incident response workflow for major degradations?

Incident response workflows for major degradations should follow a strict order: triage, severity assessment, stakeholder communication, and postmortem writing. This Skill enforces that sequence to maintain focus and speed during alert-driven response scenarios.