skills.rest
stefanbosak
stefanbosakCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

grafana-prd

Query Grafana production metrics, logs, traces, and dashboards via the grafana-prd MCP server.

Updated Jan 27, 2026
Search Tags:#dashboards#observability#alerts#grafana#prometheus#loki#tempo
One-click install
npx skills add https://github.com/stefanbosak/claude-cli --skill grafana-prd-stefanbosak
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: grafana-prd
Source: https://github.com/stefanbosak/claude-cli/tree/main/.claude/skills/grafana-prd
Command: npx skills add https://github.com/stefanbosak/claude-cli --skill grafana-prd-stefanbosak

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Access Grafana production observability data to monitor metrics, logs, traces, and dashboards, and streamline incident and alert management in production environments.

Core Features & Use Cases

  • Metrics (Prometheus): query PromQL against production data sources, list metrics, and compute percentiles.
  • Logs (Loki): search logs, filter by labels, and correlate with traces for incident analysis.
  • Traces (Tempo): analyze distributed traces to identify bottlenecks and slow paths.
  • Dashboards & Alerts: manage dashboards, create alert rules, and surface actionable insights for on-call responders.
  • Incidents & OnCall: create, list, and track incidents and on-call schedules for production systems.
  • Security & Compliance: ensure safe delegation to grafana-prd agent and MCP server.
  • Workflow & Best Practices: follow isolation guidelines and data-driven observability workflows.

Quick Start

Query Grafana production metrics for a service and review the related dashboards.

Frequently Asked Questions about grafana-prd

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

FAQPage Schema
How do I query Prometheus metrics and Loki logs for incident response?▼

Query Prometheus metrics and Loki logs for incident response by running PromQL queries, filtering logs by labels, and correlating results with Tempo traces to identify production bottlenecks.

What is the best way to manage Grafana dashboards and alert rules in production?▼

Manage Grafana dashboards and alert rules in production by creating, updating, and tracking alert configurations alongside dashboards to surface actionable insights for on-call responders.

Can I analyze distributed traces in Tempo to identify slow paths?▼

Analyze distributed traces in Tempo to identify slow paths by querying trace data to pinpoint performance bottlenecks and correlating them with metrics and logs for full incident analysis.

How do I create and track production incidents and on-call schedules?▼

Create and track production incidents and on-call schedules by managing incident records and surfacing responder schedules through the Grafana production observability agent and MCP server.

Does the Grafana production agent validate datasource permissions before operations?▼

The Grafana production agent validates datasource permissions before operations, ensuring safe delegation and compatibility with the MCP server while maintaining security and compliance isolation guidelines.

Related Skills

Explore More Software Engineering Skills→
pi-2rpi-2r

grafana-prd

Query Prometheus metrics, Loki logs, Tempo traces, and Pyroscope profiling in production.

Community
Advanced
grafanagrafana
213

alerting-irm

Configure Grafana Alerting, IRM, and SLO components via YAML or API.

Official
Advanced
williamzujkowskiwilliamzujkowski
6

Observability Unified Dashboard

Designs unified observability dashboards correlating metrics, logs, and traces across Prometheus, Loki, Tempo, and Grafana 11.

Community
Advanced
therealbilltherealbill
3

monitoring-setup

Configure Prometheus scrapes, Grafana dashboards, and Alertmanager rules for Temporal clusters.

Community
Advanced