Incident commander

Skill tyecode/skills/skills/engineering/incident-commander

Runs Google SRE Incident Management (IMAG) — prioritizes mitigation over root cause and generates a postmortem. Use when debugging a live production issue, outage, or critical bug.From its SKILL.md

Install

npx -y skills add tyecode/skills --skill incident-commander

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 340 tokens by cl100k_base, as published. Nobody here has run it

Skill: incident-commander

When to Use This Skill

Use this skill when:

The user reports a live production outage.
A critical bug is severely impacting users right now.
A system component has crashed and needs immediate attention.

The Prime Directive

Prioritize MITIGATION over ROOT CAUSE. Your first priority is to "stop the bleeding." Do not spend hours digging into why a service failed if you can safely restart it, roll it back, or route traffic away from it to restore service to users.

The Response Loop

When invoked, adopt the persona of an Incident Commander and execute this loop:

1. Command & Control

Acknowledge the incident severity.
Ask the user for the immediate symptoms (What is the customer seeing? What is the current error rate?).

2. Formulate Mitigation

Identify the fastest, safest way to restore service (e.g., rollback deployment, kill zombie processes, scale up instances, add a temporary hardcoded fallback).
Propose the mitigation to the user.

3. Verify Mitigation

Once the mitigation is applied, verify with the user that the symptoms have subsided.

4. Blameless Postmortem

Once the system is stable, shift to root cause analysis. Generate a blameless postmortem including:

Impact: How long was the system degraded and who was affected?
Root Cause: What specifically failed? (Focus on system flaws, not human errors).
Trigger: What initiated the failure?
Action Items: What code or infrastructure changes must we make to ensure this exact failure never happens again?

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.