agentleFS
Sign inStart free
cookieMonsterDevcookieMonsterDev/agents-skills/skills/docs/grafana-docs/SKILL.md

grafana-docs

Skill7 starsChanged 15 days agoMITView on GitHub

Official Grafana Labs documentation, answered with links to the exact pages. Use for any Grafana question, including dashboards and data sources, alerting, Loki, Mimir, Tempo and Pyroscope, Alloy and Beyla, k6, or Grafana Cloud.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep Grafana Cloud-only steps apart from OSS self-hosted workflows.

    line 33
  2. Distinctive:

    Check Loki label behavior in the LogQL docs rather than carrying over Prometheus label assumptions.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Grafana Docs

Grafana answers drift across versions and across the OSS, Enterprise and Cloud editions of a large docs tree, so ground each answer in the live docs at https://grafana.com/docs/, not memory, and link the exact page behind every claim.

Route OpenTelemetry SDK instrumentation without Grafana-specific collection context to opentelemetry-docs, and Kubernetes API resources or kubectl to kubernetes-docs. Prometheus scrape config with no Grafana product involved belongs to Prometheus's own docs, and third-party plugins to their own docs unless documented on grafana.com or the plugin catalog.

Workflow

  1. Locate the question in references/topic-map.md, a selective index of docs entry points. Done when each part of the question maps to a section of the map, or you have noted that none fits.
  2. Search grafana.com/docs with the user's exact terms plus Grafana vocabulary such as data source, LogQL, TraceQL, alert rule, Grafana Alloy, or Grafana Cloud, starting from the map's pages and the Routing rules below. Done when you hold the one page that most directly answers each part.
  3. Read each page down to the relevant section. Done when you have read the passage behind every claim you will make. When a page has moved, been renamed, or stops short, say so and link the nearest authoritative pages.
  4. Answer with the direct answer first, each docs link beside the claim it supports, and dashboard JSON or config only when the user asks or the page needs it. Mark any conclusion that joins several pages as Inference:. Done when every claim cites a specific page, not the docs home.

Routing

  • Versions: default to latest docs paths unless the user names a product version.
  • Broad discovery: the curated indexes at https://grafana.com/llms.txt and https://grafana.com/llms-full.txt.
  • Edition-specific steps: confirm Grafana OSS, Enterprise or Cloud first.
  • Grafana UI: Grafana OSS latest docs, before Cloud-only features.
  • Data source setup and plugins: the specific data source plugin page and the plugin catalog.
  • Signal backends: Loki for logs, Tempo for traces, Mimir for metrics storage.
  • Telemetry collection: the Alloy and Beyla docs, before legacy agent guidance.
  • Alerting: tell Grafana Alerting from legacy dashboard alerts.
  • Onboarding: the Learning Hub and Getting Started paths.

Gotchas

  • Keep Grafana Cloud-only steps apart from OSS self-hosted workflows.
  • Check Loki label behavior in the LogQL docs rather than carrying over Prometheus label assumptions.
  • Recommend Alloy, with its migration guidance, over deprecated agents.
  • Explore and dashboard query behavior can differ by data source; check that data source's page.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free