Can I modify Grafana dashboards with this skill?

Yes, you can search for dashboards, retrieve panel queries, and apply targeted patches to update dashboard structures without replacing the entire JSON model.

Does this support alerting and incident response?

Absolutely. You can list alert rules, manage contact points, view active incidents, and even check who is currently on-call for specific schedules.

What is Sift AI analysis in this context?

Sift is an AI-powered investigation tool within the Grafana stack that helps identify error patterns and slow requests by scanning your telemetry data automatically.

Why use this instead of kubectl logs?

Loki aggregates all logs across the cluster, providing superior search, filtering, and historical access compared to the limited buffer of raw kubectl output.

Do I need to configure MCP tools manually for this skill?

No, the skill uses a gateway script to invoke the Grafana MCP server on-demand, handling tool discovery and execution internally.

Grafana Cluster Observability

Name: Grafana Cluster Observability
Author: fzymgc-house

byfzymgc-house

0•

分析と監視

Manages Grafana, Loki, and Prometheus operations for unified Kubernetes cluster observability and incident response.

This skill provides a comprehensive interface for managing the fzymgc-house observability stack directly within Claude Code. It enables developers to query logs via Loki, analyze metrics with Prometheus, manage Grafana dashboards, and handle on-call incidents without leaving the terminal. By prioritizing aggregated logs and time-series data over standard Kubernetes API calls, it streamlines debugging and system monitoring through specialized workflows like log investigation, metric exploration, and AI-powered Sift analysis.

主な機能

01Integrated incident management and OnCall schedule tracking

020 GitHub stars

03Prometheus time-series metrics and PromQL exploration

04Unified Loki log aggregation with LogQL query support

05Full Grafana dashboard management including searching and patching

06AI-powered log pattern analysis and Pyroscope performance profiling

ユースケース

01Creating or updating Grafana dashboards to monitor new service deployments

02Troubleshooting application errors by analyzing aggregated cluster logs and metrics

03Managing on-call shifts and investigating active incidents using automated Sift analysis

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add fzymgc-house/fzymgc-house-skills grafana

For use in Claude.ai and ChatGPT

主な機能

01Integrated incident management and OnCall schedule tracking

020 GitHub stars

03Prometheus time-series metrics and PromQL exploration

04Unified Loki log aggregation with LogQL query support

05Full Grafana dashboard management including searching and patching

06AI-powered log pattern analysis and Pyroscope performance profiling

ユースケース

01Creating or updating Grafana dashboards to monitor new service deployments

02Troubleshooting application errors by analyzing aggregated cluster logs and metrics

03Managing on-call shifts and investigating active incidents using automated Sift analysis

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add fzymgc-house/fzymgc-house-skills grafana

For use in Claude.ai and ChatGPT