debug-with-grafana

Diagnoses application issues using Grafana metrics, logs, and traces.

535|42|Updated Mar 23, 2026

Search Tags:#debugging #logs #metrics #observability #diagnostics #grafana #traces

Ready to run

npx skills add https://github.com/grafana/gcx --skill debug-with-grafana

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: debug-with-grafana
Source: https://github.com/grafana/gcx/tree/main/claude-plugin/skills/debug-with-grafana
Command: npx skills add https://github.com/grafana/gcx --skill debug-with-grafana

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnosing and triaging application issues can be time-consuming; this skill provides a structured Grafana observability workflow to systematically identify root causes using metrics, logs, and traces.

Core Features & Use Cases

Stepwise diagnostic workflow covering discovery, data availability, error rates, latency, log and trace correlation, dashboards, and remediation.
Uses Grafana data sources (Prometheus, Loki, Tempo) to compile evidence during outages or performance degradation.
Real-world use: Investigate API latency spikes with correlated logs and traces to isolate faulty dependencies.

Quick Start

Initiate the diagnostic workflow by running gcx commands to collect metrics, logs, and traces and follow the step-by-step guidance to produce a coordinated incident analysis.

Frequently Asked Questions about debug-with-grafana

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

FAQPage Schema

How do I debug application latency spikes using Grafana metrics, logs, and traces?▼

Debug application latency spikes by following a structured Grafana observability workflow that correlates Prometheus metrics, Loki logs, and Tempo traces to isolate faulty dependencies and rapidly identify root causes.

What is the best way to triage outages and perform root-cause analysis with observability data?▼

Triage outages using a stepwise Grafana workflow that gathers evidence from Prometheus, Loki, and Tempo, correlates observability signals across error rates and latency, and produces an actionable incident summary for rapid remediation.

Do I need Prometheus, Loki, and Tempo configured to diagnose issues with this observability workflow?▼

Yes, this diagnostic workflow collects and correlates data specifically from Prometheus for metrics, Loki for logs, and Tempo for traces to ensure comprehensive evidence gathering during outages or performance degradation.

How do I start correlating logs and traces to investigate API errors in Grafana?▼

Start investigating API errors by running gcx commands to collect observability data, then follow the step-by-step guidance to correlate Loki logs with Tempo traces and compile coordinated evidence for incident analysis.

Does this Grafana diagnostics workflow cover dashboard creation and remediation guidance?▼

Yes, the stepwise diagnostic workflow covers discovery, data availability checks, error rate analysis, latency analysis, log and trace correlation, dashboard review, and ultimately produces actionable remediation guidance.