triage-dev

Investigate root causes of shared development environment failures via observability sources.

4|Updated Jul 20, 2026
One-click install
npx skills add https://github.com/highflame-ai/ai-factory --skill triage-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: triage-dev
Source: https://github.com/highflame-ai/ai-factory/tree/main/skills/triage-dev
Command: npx skills add https://github.com/highflame-ai/ai-factory --skill triage-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill eliminates speculative debugging in shared development environments by providing a structured, observability-driven investigation process that localizes failures to specific services, spans, or data states.

Core Features & Use Cases

  • Observability-First Triage: Automatically follows configured tracing and dashboard sources to pinpoint the exact service and operation where a failure originates.
  • Runbook Integration: Detects and follows existing organizational runbooks to ensure investigations align with established institutional knowledge.
  • Use Case: When a shared dev environment reports a 500 error after a deployment, this skill guides the agent to verify traces, orchestrator health, and data consistency in the correct order to identify if the issue is a configuration drift, a bad image, or corrupted data.

Quick Start

Use the triage-dev skill to investigate the current error spike in the shared development environment by following the configured observability order.

Frequently Asked Questions about triage-dev

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

FAQPage Schema
How do I find the root cause of a 500 error in a shared development environment?

Root cause analysis for development environments systematically queries observability sources and orchestrator state to localize failures to specific services or data states. It eliminates speculative debugging by following a structured, observability-driven investigation process.

What is the best way to investigate latency spikes and integration test failures in non-production environments?

Investigating latency spikes in non-production environments requires automatically following configured tracing and dashboard sources to pinpoint the exact service and operation where failures originate. This approach verifies service health and configuration state in the correct order.

Do I need tracing and dashboard tools configured to troubleshoot service errors in dev environments?

Yes, troubleshooting service errors in dev environments requires access to configured tracing, dashboarding, and cluster management tools to verify service health and configuration state. The investigation follows these observability sources to localize failures accurately.

Can I use observability-driven triage to detect configuration drift or bad images after a deployment?

Observability-driven triage identifies configuration drift, bad images, or corrupted data after a deployment by verifying traces, orchestrator health, and data consistency. It guides investigations through the correct order to determine the exact issue type.

How does runbook integration work during incident response in development environments?

Runbook integration during incident response detects and follows existing organizational runbooks to ensure investigations align with established institutional knowledge. This ensures troubleshooting respects established procedures while querying observability sources and orchestrator state.