dashboard-builder

What this skill does

When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.

---
name: dashboard-builder
description: Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms. Use when turning metrics into a working dashboard instead of a vanity board.
origin: ECC direct-port adaptation
version: "1.0.0"
---

# Dashboard Builder

Use this when the task is to build a dashboard people can operate from.

The goal is not "show every metric." The goal is to answer:

- is it healthy?
- where is the bottleneck?
- what changed?
- what action should someone take?

## When to Use

- "Build a Kafka monitoring dashboard"
- "Create a Grafana dashboard for Elasticsearch"
- "Make a SigNoz dashboard for this service"
- "Turn this metrics list into a real operational dashboard"

## Guardrails

- do not start from visual layout; start from operator questions
- do not include every available metric just because it exists
- do not mix health, throughput, and resource panels without structure
- do not ship panels without titles, units, and sane thresholds

## Workflow

### 1. Define the operating questions

Organize around:

- health / availability
- latency / performance
- throughput / volume
- saturation / resources
- service-specific risk

### 2. Study the target platform schema

Inspect existing dashboards first:

- JSON structure
- query language
- variables
- threshold styling
- section layout

### 3. Build the minimum useful board

Recommended structure:

1. overview
2. performance
3. resources
4. service-specific section

### 4. Cut vanity panels

Every panel should answer a real question. If it does not, remove it.

## Example Panel Sets

### Elasticsearch

- cluster health
- shard allocation
- search latency
- indexing rate
- JVM heap / GC

### Kafka

- broker count
- under-replicated partitions
- messages in / out
- consumer lag
- disk and network pressure

### API gateway / ingress

- request rate
- p50 / p95 / p99 latency
- error rate
- upstream health
- active connections

## Quality Checklist

- [ ]

Use this skill

{
  "model": "gpt-4o-mini",
  "skill": "imp-1fe02e25-184f-4711-b115-375af936d7df",
  "messages": [{ "role": "user", "content": "…" }]
}

More skills