skills.rest
Lifecycle-Innovations-Limited
Lifecycle-Innovations-LimitedOFFICIAL
Explore all skills by this author →
Website𝕏@healifyappGitHub

ops-fires

Aggregate ECS health, Sentry errors, and CI failures to detect production incidents.

22|6|Updated Apr 11, 2026
Search Tags:#automation#agent#ecs#sentry#ci#incident#fires
One-click install
npx skills add https://github.com/Lifecycle-Innovations-Limited/claude-ops --skill ops-fires
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ops-fires
Source: https://github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/claude-ops/skills/ops-fires
Command: npx skills add https://github.com/Lifecycle-Innovations-Limited/claude-ops --skill ops-fires

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Production incidents across ECS health, Sentry errors, and CI failures can cascade quickly if not detected early. This skill aggregates signals and surfaces active fires to enable rapid containment and informed decision-making.

Core Features & Use Cases

  • Real-time incident detection by querying ECS health, Sentry MCP, and recent CI failures.
  • Automated agent dispatch to investigate root causes, create fixes, and open PRs for review.
  • Optional team coordination through Agent Teams to accelerate multi-service firefighting and post-mortem learning.

Quick Start

Start the OPS FIRES dashboard to monitor ECS health, Sentry errors, and CI failures and triage active fires.

Frequently Asked Questions about ops-fires

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

FAQPage Schema
How do I detect production incidents by aggregating ECS health and Sentry errors?▼

You can detect production incidents by querying ECS health, Sentry MCP, and recent CI failures to aggregate signals and surface active fires for rapid containment. This skill coordinates investigation and dispatches agents to triage these events.

Can I automatically dispatch fix agents to investigate and open PRs for CI failures?▼

Yes, automated agent dispatch is supported to investigate root causes, create fixes, and open PRs for review. Agents use pre-gathered infrastructure data and secret resolution to coordinate remediation workflows for critical fires.

Does this incident response skill support monitoring all projects at once?▼

Yes, you can apply monitoring across projects or all projects by using a project alias or specifying all. This allows you to classify severity and route fix agents for critical fires across multiple services simultaneously.

What's the best way to coordinate multi-service firefighting during a production incident?▼

Optional team coordination through Agent Teams accelerates multi-service firefighting and post-mortem learning. It enables multiple agents to work together on incident investigation, fix creation, and PR generation.

How do I classify severity for critical fires detected from Sentry errors?▼

Severity classification for critical fires is handled by aggregating Sentry errors, ECS health, and CI failures, then routing fix agents based on the detected severity. This ensures informed decision-making and rapid containment.

Related Skills

Explore More Software Engineering Skills→
ChatAndBuildChatAndBuild
1

ci-monitor

Monitor CI pipeline health and prioritize failing jobs with remediation steps.

Official
Advanced
hpsgdhpsgd

incident-response

Coordinate phase-driven incident response workflows with mandatory timelines and auditable records.

Official
Advanced
magnus919magnus919
40

woodpecker-ci

Operate and troubleshoot Woodpecker CI deployments, pipelines, and incidents.

Community
Advanced
tarunccettarunccet
5

ai-incident-response

Classify and respond to AI model failures with severity runbooks.

Community
Advanced