# metric-diagnostics

This skill investigates metric changes, anomalies, gaps, and mismatches with expectations. Use it when you need evidence for likely drivers.

- skill · `type=skill` · Codex, ChatGPT · 4 installs · ★ 7604
- Author: Data Analytics Maintainers · official OpenAI repository
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/openai/plugins/tree/HEAD/plugins/data-analytics/skills/metric-diagnostics/SKILL.md
- Updated: 2026-10-08
- HTML: https://affpapa.org/en/nevibecode/skills/metric-diagnostics

## What it does

The skill frames the diagnostic question before searching for causes. It clarifies the metric meaning, comparison window, population, grain, and owning source, then reproduces the calculation and measures the size, timing, and scope of the movement.

It searches relevant data surfaces, compares overlapping sources, and checks definitions, filters, joins, freshness, lineage, and aggregation. Driver analysis can use semantic layers, dashboards, tables, and other source-of-truth surfaces; fresh SQL or Python work can be recorded with `jupyter-notebooks`.

When a required source cannot be accessed, the skill stops that analysis path and asks for the source or a reviewed fallback. Related skills cover business context, data quality, and recommendations after the diagnosis.

## Install

### Codex (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill metric-diagnostics -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/metric-diagnostics/SKILL.md` — For all projects use ~/.agents/skills/

### Claude Code

1. **Skills CLI (Vercel)**
```bash
npx skills add openai/plugins --skill metric-diagnostics -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/metric-diagnostics/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/metric-diagnostics/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/metric-diagnostics/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install openai/plugins metric-diagnostics
```

2. **Manually: put the files in place**
- File: `.github/skills/metric-diagnostics/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/openai/plugins --path plugins/data-analytics/skills/metric-diagnostics
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/metric-diagnostics/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/openai/plugins/tree/HEAD/plugins/data-analytics/skills/metric-diagnostics/SKILL.md

## When to use it
- explain why a metric moved
- reproduce a comparison against a baseline
- rank the segments driving a change
- reconcile a gap between data sources
- test whether a spike reflects data-quality issues

## Example prompts
- Diagnose why conversion changed between the two periods and quantify the segment contributions.
- Investigate the mismatch between the dashboard metric and the source table.
- Analyze the error spike: locate its onset, affected slices, and verified drivers.

## Similar
- [kibana-anomaly-detection](https://affpapa.org/en/nevibecode/skills/kibana-anomaly-detection.md) — skill · 3100 installs
- [cloud-monitoring-metric-selection](https://affpapa.org/en/nevibecode/skills/cloud-monitoring-metric-selection.md) — skill · 5453 installs
- [dt-obs-predictive-analytics](https://affpapa.org/en/nevibecode/skills/dt-obs-predictive-analytics.md) — skill · 2100 installs
- [launchdarkly-metric-create](https://affpapa.org/en/nevibecode/skills/launchdarkly-metric-create.md) — skill · 3200 installs
- [elasticsearch-anomaly-detection-explainer](https://affpapa.org/en/nevibecode/skills/elasticsearch-anomaly-detection-explainer.md) — skill · 1000 installs
- [iot-anomalies](https://affpapa.org/en/nevibecode/skills/iot-anomalies.md) — skill · 730 installs

From the same set: [openai/plugins](https://affpapa.org/en/nevibecode/by/openai/plugins.md) — 528 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md