How do I install the Grafana skill?

Run npx skillmds@latest add jylhis/grafana in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Grafana safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Grafana?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Grafana free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Grafana?

Jylhis (@jylhis) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Grafana by jylhis — Agent Skill

Name: Grafana
Author: Jylhis

Grafana

Grafana observability umbrella — routes to the right Grafana sub-skill for the task. Use when the user mentions Grafana generally or asks about observability, dashboards, alerting, or monitoring without naming a specific sub-area, or when you need to figure out which Grafana skill applies. Covers: alerting and IRM (alert rules, contact points, notification policies, on-call, SLOs), dashboard authoring (panel types, JSON, variables, transformations, API push), OpenTelemetry instrumentation (SDK, OTLP, Alloy, sampling), Grafana OSS (provisioning, data sources, grafana.ini, roles), and PromQL (rate, aggregation, histogram_quantile, recording rules, cardinality). Read the routing table below, then load the specific sub-skill.

Jylhis 70ed320 2.3 KB Updated Sep 17, 2026

File contents

Grafana skill index

This is a router. Pick the sub-skill that matches the task and read its SKILL.md before acting. Each sub-skill is the focused, opinionated guidance for that Grafana area.

Sub-skill	When to use	Path
Grafana alerting	Alert rules, contact points (Slack/PagerDuty/email), notification policies, silences, on-call schedules, SLOs, incident management	`grafana-alerting/SKILL.md`
Grafana dashboarding	Build/modify dashboards as JSON via HTTP API; panel types, gridPos layout, variables, transformations, annotations	`grafana-dashboarding/SKILL.md`
Grafana OpenTelemetry	Instrument apps with OTel; ship metrics/logs/traces to Grafana Cloud or self-hosted Mimir/Loki/Tempo; Beyla eBPF; sampling	`grafana-opentelemetry/SKILL.md`
Grafana OSS	Provisioning from YAML, data sources, grafana.ini config, roles, service-account tokens, plugins, local Grafana	`grafana-oss/SKILL.md`
Grafana PromQL	Write, validate, optimize PromQL queries; rate vs irate, aggregation, histogram_quantile, recording rules, cardinality hunting	`grafana-promql/SKILL.md`

Common rules across all Grafana sub-skills

Confirm the Grafana stack is reachable before any API call. Use the health-check endpoint (GET /api/health) to verify connectivity.
After every dashboard API push, verify with the returned version plus a GET on the dashboard UID.
For PromQL queries, the golden rule: rate() / increase() require a range vector >= 4x the scrape interval.

After reading the sub-skill, follow its guidance for the task.

---name: grafanadescription: Grafana observability umbrella — routes to the right Grafana sub-skill for the task. Use when the user mentions Grafana generally or asks about observability, dashboards, alerting, or monitoring without naming a specific sub-area, or when you need to figure out which Grafana skill applies. Covers: alerting and IRM (alert rules, contact points, notification policies, on-call, SLOs), dashboard authoring (panel types, JSON, variables, transformations, API push), OpenTelemetry instrumentation (SDK, OTLP, Alloy, sampling), Grafana OSS (provisioning, data sources, grafana.ini, roles), and PromQL (rate, aggregation, histogram_quantile, recording rules, cardinality). Read the routing table below, then load the specific sub-skill.---# Grafana skill indexThis is a router. Pick the sub-skill that matches the task and read its`SKILL.md` before acting. Each sub-skill is the focused, opinionatedguidance for that Grafana area.| Sub-skill | When to use | Path ||---|---|---|| Grafana alerting | Alert rules, contact points (Slack/PagerDuty/email), notification policies, silences, on-call schedules, SLOs, incident management | `grafana-alerting/SKILL.md` || Grafana dashboarding | Build/modify dashboards as JSON via HTTP API; panel types, gridPos layout, variables, transformations, annotations | `grafana-dashboarding/SKILL.md` || Grafana OpenTelemetry | Instrument apps with OTel; ship metrics/logs/traces to Grafana Cloud or self-hosted Mimir/Loki/Tempo; Beyla eBPF; sampling | `grafana-opentelemetry/SKILL.md` || Grafana OSS | Provisioning from YAML, data sources, grafana.ini config, roles, service-account tokens, plugins, local Grafana | `grafana-oss/SKILL.md` || Grafana PromQL | Write, validate, optimize PromQL queries; rate vs irate, aggregation, histogram_quantile, recording rules, cardinality hunting | `grafana-promql/SKILL.md` |## Common rules across all Grafana sub-skills- Confirm the Grafana stack is reachable before any API call. Use the health-check endpoint (`GET /api/health`) to verify connectivity.- After every dashboard API push, verify with the returned `version` plus a GET on the dashboard UID.- For PromQL queries, the golden rule: `rate()` / `increase()` require a range vector >= 4x the scrape interval.After reading the sub-skill, follow its guidance for the task.

Frequently asked questions