SweetClaude Something Broke

Guide production incident triage through diagnostic questioning and severity classification.

6|3|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/carson-sweet/sweetclaude --skill sweetclaude-something-broke
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: SweetClaude Something Broke
Source: https://github.com/carson-sweet/sweetclaude/tree/main/skills/something-broke
Command: npx skills add https://github.com/carson-sweet/sweetclaude --skill sweetclaude-something-broke

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a disciplined, step-by-step framework for handling production incidents, ensuring that triage is fast, consistent, and well-documented without skipping critical safety checks.

Core Features & Use Cases

  • Structured Triage: Guides the user through a 3-question diagnostic process to classify severity and identify root causes.
  • Resolution Management: Facilitates a clear decision-making process between rolling back changes or patching in-place.
  • Post-Incident Accountability: Enforces mandatory post-mortem creation to ensure long-term system stability and prevent recurrence.

Quick Start

Invoke the something broke skill to begin a structured triage process for a current production incident.

Frequently Asked Questions about SweetClaude Something Broke

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

FAQPage Schema
How do I triage a production incident?

To triage a production incident, you guide users through a 3-question diagnostic process to classify severity and identify root causes before selecting a resolution path.

What is the best way to decide between a rollback and a hotfix during an incident?

The best way to choose between a rollback and a hotfix is using a structured resolution management process that evaluates repository state and git history to facilitate clear decision-making.

How do I enforce post-mortem documentation after resolving an incident?

You enforce post-mortem documentation by integrating mandatory post-incident accountability steps into your triage workflow, ensuring long-term system stability and preventing recurrence.

Do I need access to git history and runbooks for incident triage?

Yes, incident triage requires access to repository state, git history, and incident runbooks to ensure context-aware recovery within live software environments.

What is structured incident triage and when do I need it?

Structured incident triage is a disciplined framework for handling production incidents, needed when you require fast, consistent, and well-documented recovery without skipping critical safety checks.