Grafana Dashboards Skill for Claude: Build Dashboards and Provisioning Files

Gives Claude a Grafana reference for designing dashboards, writing panel JSON and variables, and provisioning them as code.

Installs: 13.4K; on skills.sh
Stars: 42.1K; on GitHub
Updated: Oct 2026; last repo commit

grafana-dashboards is a single-file reference that Claude reads when you ask for a monitoring dashboard. SKILL.md covers dashboard layout (big numbers first, then trends, then detail), the RED method for services and the USE method for resources, and a full API monitoring dashboard as JSON.

It also gives example JSON for stat, time series, table and heatmap panels, query variables, alert rules in a dashboard, file provisioning with a dashboards.yml, and dashboards as code with Terraform and Ansible. It bundles no scripts, and it triggers on requests to build monitoring dashboards or visualize metrics. SKILL.md lists prometheus-configuration and slo-implementation as related skills.

Good for

SREs and developers building Grafana dashboards over Prometheus metrics
Teams that want dashboards stored as JSON, Terraform or Ansible instead of clicked together
Anyone who wants API, database or infrastructure dashboards with sensible default panels

Install grafana-dashboards

Claude Code

Copy this prompt.

Install the grafana-dashboards skill in Claude Code. Run this command:

/plugin marketplace add wshobson/agents
/plugin install observability-monitoring@claude-code-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole observability-monitoring plugin: 4 agents, 2 commands and 4 skills (counted from the plugin folder in the repo tree, which has no hooks or MCP config files). The skills-only routes install just this skill, with no agents or commands. The skill itself is a reference file; applying its Terraform or Ansible examples needs your own Grafana host and those tools.

From the project README. Source.

What's in the skill

When it loads

Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.

Sections in SKILL.md

Purpose
When to Use
Dashboard Design Principles
1. Hierarchy of Information
2. RED Method (Services)
3. USE Method (Resources)
Dashboard Structure
API Monitoring Dashboard
Panel Types
1. Stat Panel (Single Value)
2. Time Series Graph
3. Table Panel
4. Heatmap
Variables
Query Variables
Use Variables in Queries

Key facts

Author: wshobson (repo owner)
License: MIT
Installs on skills.sh: 13,358 as of 2026-11-02
GitHub stars: 42,081 for the whole repo
Last commit to the repo: 2026-10-30
Files in the skill: 1 file: SKILL.md
skills.sh audits: Gen Agent Trust Hub pass, Socket pass, Snyk pass
Related skills named in SKILL.md: prometheus-configuration, slo-implementation

What it includes

Puts big numbers first, then trends, then detail tables.
Also describes the RED method (rate, errors, duration) for services and the USE method (utilization, saturation, errors) for resources.
Read · Dashboard design principles
A complete dashboard JSON with request rate, error rate and P95 latency.
Three panels with Prometheus queries, a 30 second refresh and an error-rate alert condition.
Try: “Build a Grafana dashboard for my API with request rate, error rate and p95 latency.”
Read · API Monitoring Dashboard
Example JSON for stat, time series, table and heatmap panels.
Each panel type comes with a worked JSON example, including thresholds for the stat panel.
Read · Panel types
Query variables and how to use them in panel queries.
Shows namespace and service variables used in a Prometheus query.
Read · Variables
An example alert definition inside a dashboard.
A JSON example of alert settings attached to a panel.
Read · Alerts in dashboards
A dashboards.yml that loads dashboard files from a folder.
Shows a file provider reading JSON from /etc/grafana/dashboards.
Files · Dashboard provisioning
Key panels for infrastructure, database and application dashboards.
Lists the panels to include for each, such as CPU per node, replication lag and cache hit rate.
Read · Common dashboard patterns
Ten rules, such as consistent naming, variables and sensible thresholds.
Includes starting from community templates and testing with different time ranges.
Read · Best practices
Terraform and Ansible examples that deploy dashboard JSON.
The Terraform example creates a grafana_dashboard and a grafana_folder. The Ansible example copies JSON files to /etc/grafana/dashboards/ and restarts Grafana.
Write · Dashboard as code

From the official docs

Permissions

Low risk

The skill is guidance only, but its Terraform and Ansible examples would change a Grafana server if you applied them. Review the plan before you apply it.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Its deploy examples change a Grafana server
SKILL.md shows Terraform that creates a dashboard and folder, and Ansible that copies JSON to /etc/grafana/dashboards/ and notifies a restart. Nothing runs by itself, so review the plan or playbook before applying it. github.com
The plugin route adds more than this skill
The observability-monitoring plugin also installs 4 agents (database-optimizer, network-engineer, observability-engineer, performance-engineer), 2 commands (monitor-setup, slo-implement) and 3 other skills. The repo tree shows no hooks or MCP config files in it. The skills CLI route installs only this skill. github.com

Technical details

Scopes	The Terraform and Ansible examples in SKILL.md create or copy dashboard files on a Grafana host if you run them

Questions

What does the grafana-dashboards skill do?

It gives Claude a reference for building Grafana dashboards: layout rules, the RED and USE methods, example panel JSON, variables, provisioning and Terraform or Ansible deployment. Claude uses it when you ask for a monitoring dashboard.

How do I install grafana-dashboards?

Use the install box above. The skills CLI command installs only this skill, which is one SKILL.md file. The plugin route installs the whole observability-monitoring plugin, with its agents and commands.

Does it connect to my Grafana?

SKILL.md bundles no scripts and names no Grafana URL or API key. It teaches Claude what to write. You paste or import the JSON yourself, or use the Terraform or Ansible examples it shows.

Is grafana-dashboards safe to use?

It is a reference file, but the dashboards-as-code section shows Terraform and Ansible that would change a real Grafana server if you run them. Read what Claude writes and test on a non-production Grafana first.

grafana-dashboards vs prometheus-configuration?

This skill covers dashboards. SKILL.md points to prometheus-configuration for collecting metrics and slo-implementation for SLO dashboards. Those are separate skills you install on their own.

Information

updated Nov 2, 2026

Repository: wshobson/agents
Folder: plugins/observability-monitoring/skills/grafana-dashboards

wshobson/agents skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

grafana-dashboards SKILL.md · github.com
wshobson/agents README · github.com
observability-monitoring plugin.json · github.com
SKILL.md · github.com
agents README · github.com