agentleFS
NVIDIAKnown publisherNVIDIA/AI-Factory-Operations-Agent/helm/mosaic-stack/files/openclaw-seed/skills/grafana/SKILL.md

grafana

Skill37 starsChanged 10 days agoApache-2.0View on GitHub

Create and open Grafana dashboards for metrics, Loki logs, and mixed panels. Use when the user asks for a dashboard, visualization, chart, panel, or graph of GPU, Base Command Manager (BCM), node, network, InfiniBand, Prometheus metrics, or Loki logs.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use grafana_dashboard_create to build a dashboard from PromQL and LogQL panels and open it in the UI Grafana tab.

    line 21
  2. Distinctive:

    Always validate queries before claiming success.

    line 23
  3. Very specific:

    If validation fails, inspect its issues and availableDatasources.

    line 47
  4. Very specific:

    Create the requested panels and inspect the result.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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
<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: Apache-2.0 -->

grafana — Dashboard Builder

Use grafana_dashboard_create to build a dashboard from PromQL and LogQL panels and open it in the UI Grafana tab.

Always validate queries before claiming success. The create tool validates each panel and returns actionable errors if a query is invalid or empty.

Example PromQL queries; verify metric names and source labels before using them:

  • max by (Hostname, gpu) (DCGM_FI_DEV_GPU_TEMP)
  • avg by (Hostname) (DCGM_FI_DEV_GPU_UTIL)
  • avg by (Hostname, gpu) (DCGM_FI_DEV_POWER_USAGE)
  • rate(bcm_network_receive_bytes_total[5m])
  • rate(bcm_infiniband_port_data_received_bytes_total[5m])

Dashboard authoring and access

Dashboard creation is available in View mode: it saves visualizations without changing monitored workloads or infrastructure. Use the dashboard tools rather than generic execution or asking users to import JSON manually.

Dashboards may mix Prometheus and Loki panels.

  1. Discover datasource names, types, and UIDs with dashboard_list or grafana_dashboard_presets. Both return a datasources list; dashboard_list returns it even when its dashboard search has no matches. Dashboard UIDs, datasource UIDs, and Loki source labels are different identifiers.
  2. Pass panels as a JSON array of objects. For each Loki panel, use datasource: {type: "loki", uid: "<discovered UID>"} and a grounded LogQL query; use visualization: "logs" for raw log lines. Prometheus panels accept a discovered datasource or the configured default.
  3. If validation fails, inspect its issues and availableDatasources. Correct the affected UID/type using the returned choices. Do not guess a UID or repeat an unchanged failed call. If no suitable datasource exists in that list, report the configuration gap.
  4. An empty query result describes the selected source and time window. Check source labels and timestamps before concluding data is unavailable. When the user has not specified a window, check a broader supported window and state the range used; preserve explicitly requested incident windows.
  5. Create the requested panels and inspect the result. created: true confirms creation, but success also requires the panels to match the requested sources and content. Do not silently substitute unrelated metrics or omit requested logs. Report any unavailable part and the evidence for it.

Each panel is validated against its selected datasource and the UI proxy before saving. A missing datasource and a valid query with no matching data require different corrections; use the tool's returned evidence to distinguish them.

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.