grafana-dash-builder

Generate Grafana dashboard JSON from natural-language requirements.

Updated May 25, 2026
One-click install
npx skills add https://github.com/mynameisi/grafana-dash-builder-skill --skill grafana-dash-builder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grafana-dash-builder
Source: https://github.com/mynameisi/grafana-dash-builder-skill/tree/main
Command: npx skills add https://github.com/mynameisi/grafana-dash-builder-skill --skill grafana-dash-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bash, curl, jq, date, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Grafana dashboard creation becomes slow and risky when you cannot quickly confirm what datasources, metrics, labels, and existing dashboards actually exist.

Core Features & Use Cases

  • Credential-safe Grafana access: reads GRAFANA_URL and GRAFANA_TOKEN only from the project-local .env and avoids asking for secrets in chat.
  • Grafana discovery + dashboard drafting: discovers Grafana version, datasources, folders, and existing dashboards, then drafts correct dashboard JSON with stable UIDs.
  • Datasource probing before generating panels: verifies that the requested data exists by querying metrics/labels/logs before producing panels, reducing broken dashboards.
  • Push and verify: uploads the dashboard to Grafana and fetches it back to confirm what was stored.

Quick Start

Ask the agent to create a Grafana dashboard for your use case, then run the setup check command from your project root if prompted: bash .cursor/skills/grafana-dash-builder/scripts/gf.sh check.

Frequently Asked Questions about grafana-dash-builder

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

FAQPage Schema
How do I generate a Grafana dashboard from natural language requirements?

You can generate a Grafana dashboard from natural language by having the agent discover datasources, probe metrics and labels, draft dashboard JSON, and push it to your instance. This discover-probe-generate-push-verify workflow ensures panels query valid data.

How can I securely create Grafana dashboards without exposing API tokens in chat?

To avoid exposing API tokens, the Skill sources GRAFANA_URL and GRAFANA_TOKEN exclusively from a project-local .env file. This credential hygiene approach prevents secrets from leaking into chat history during dashboard generation.

Can I validate Prometheus metrics and Loki LogQL queries before generating dashboard panels?

Yes, you can validate Prometheus metrics and Loki LogQL queries before generating panels because the Skill probes data sources directly. It queries metrics, labels, and logs to confirm the requested data exists before producing dashboard JSON.

Does this approach to building Grafana dashboards work with Mimir and Loki data sources?

Yes, this approach works with Prometheus, Mimir, and Loki data sources. The Skill discovers available datasources and validates metric or LogQL queries across these specific platforms before drafting and pushing dashboard panels.

What are the limitations of using bash and curl to automate Grafana dashboard generation?

Using bash and curl limits you to CLI-driven workflows requiring jq and date dependencies. The Skill enforces schemaVersion matching and UID stability, but relies entirely on local .env credentials rather than interactive secret prompts.