How does this skill ensure safety during a live outage?

It enforces a 'no destructive commands' rule without explicit approval, focuses on minimal surgical fixes rather than large refactors, and requires a rollback plan for every action.

What monitoring tools are supported?

The skill is designed to guide Claude in gathering data from common observability platforms like Prometheus, Grafana, and standard application log streams.

What is the primary purpose of the Incident Mode skill?

It provides a safe, structured process for triaging and resolving production incidents, ensuring Claude follows SRE best practices during high-pressure outages.

Can it help with post-incident reporting?

Yes, one of the core steps is preserving evidence and metrics during the triage process to facilitate detailed postmortem documentation.

Does it automatically apply fixes to production?

No, it proposes minimal fixes or mitigations that require user review and approval, always accompanied by a safety-first rollback strategy.

Incident Mode

Name: Incident Mode
Author: jibaxZZZ

byjibaxZZZ

分析と監視

Triages production incidents with safe log gathering, minimal risk mitigations, and comprehensive rollback planning.

概要

Incident Mode provides a structured framework for Claude to handle production outages and critical system failures with a focus on safety and stability. It guides the AI to prioritize systematic triage, identifying the scope of impact via Prometheus, Grafana, or application logs before suggesting any surgical fixes. By emphasizing minimal, non-destructive changes over risky refactors and mandating a clear rollback strategy, this skill ensures that emergency response is handled with professional-grade caution and rigorous evidence preservation for postmortem analysis.

主な機能

0 GitHub stars
Structured incident triage and scope identification
Safe log and metric gathering from Prometheus and Grafana
Minimal-risk mitigation strategies to avoid accidental escalation
Comprehensive rollback planning for every proposed fix
Evidence preservation for accurate post-incident follow-ups

ユースケース

Diagnosing and resolving sudden production system outages
Safely investigating performance degradation in live environments
Implementing emergency hotfixes with built-in recovery paths

概要

主な機能

0 GitHub stars
Structured incident triage and scope identification
Safe log and metric gathering from Prometheus and Grafana
Minimal-risk mitigation strategies to avoid accidental escalation
Comprehensive rollback planning for every proposed fix
Evidence preservation for accurate post-incident follow-ups

ユースケース

Diagnosing and resolving sudden production system outages
Safely investigating performance degradation in live environments
Implementing emergency hotfixes with built-in recovery paths