# earth2studio-discover

Finds compatible Earth2Studio models, data sources, and gallery examples for climate workflows. It focuses on discovery, not inference code or data downloads.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1900 installs · ★ 3735
- Author: NVIDIA Earth-2 Team
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/NVIDIA/skills/tree/HEAD/skills/earth2studio-discover/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/earth2studio-discover

## What it does

The skill queries live documentation on nvidia.github.io to discover Earth2Studio prognostic and diagnostic models. It filters options using documentation badges: forecast class, target region, and VRAM limits ranging from 40GB to 96GB.

Its core technical function is checking model-to-data compatibility. The agent compares required input dimensions from `input_coords()` against the `VOCAB` dictionary defined in the source lexicon files. Once matched, it references one or two applicable scripts from the official gallery.

Live internet access is required. This skill only evaluates compatibility and architecture: it will not write inference routines or download dataset files.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill earth2studio-discover -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/earth2studio-discover/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/earth2studio-discover/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill earth2studio-discover -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/earth2studio-discover/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill earth2studio-discover -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/earth2studio-discover/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NVIDIA/skills earth2studio-discover
```

2. **Manually: put the files in place**
- File: `.github/skills/earth2studio-discover/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill earth2studio-discover -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NVIDIA/skills --path skills/earth2studio-discover
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/earth2studio-discover/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill earth2studio-discover -a opencode
```

### 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/NVIDIA/skills/tree/HEAD/skills/earth2studio-discover/SKILL.md

## When to use it
- select weather models based on GPU VRAM limits
- verify data source compatibility using Earth2Studio lexicon VOCAB
- find relevant gallery examples for downscaling or data assimilation
- identify data sources covering required atmospheric variables

## Example prompts
- Recommend an Earth2Studio model for medium-range global forecasting on a 48GB GPU
- Check if the GFS data source provides all variables needed by GraphCastOperational
- Find a gallery workflow demonstrating CorrDiff downscaling

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: cf3da725f13a9e0a.

BEGIN THIRD-PARTY FILE cf3da725f13a9e0a
```text
---
name: earth2studio-discover
version: 0.16.0
license: Apache-2.0
metadata:
  author: NVIDIA Earth-2 Team
  tags:
    - earth2studio
    - earth2
    - python
    - discovery
    - models
    - data-sources
description: >
  Find Earth2Studio models, data sources, and examples for a weather/climate use
  case. Do NOT use for writing inference code, downloading data, or installation.
---

# Earth2Studio Discoverability Skill

## Purpose

Help users identify the right Earth2Studio models, data sources, and examples for
their weather/climate task. Use when: comparing models by GPU/VRAM requirements,
choosing forecast class (nowcast, medium-range, seasonal), finding compatible
data sources via lexicons, or locating gallery examples for downscaling,
ensemble generation, or data assimilation.

## Prerequisites

- Internet access to fetch live documentation pages from nvidia.github.io
- Familiarity with Earth2Studio badge system (Class, Region, VRAM, Release)

You are helping a user find the right Earth2Studio components for their use case. Your job is to understand what they want to do, then point them at the models, data sources, and examples that fit — verified against live documentation.

## Core principle: discover from live docs, don't memorize

Earth2Studio adds models, data sources, and examples every release. Model classes get new badges, new data sources appear, examples get reorganized. Any static list in this skill will rot.

**Rules:**
1. Always fetch the relevant live doc pages before recommending components.
2. Use badge metadata (Region, Class, VRAM, Release) from the docs to filter candidates.
3. Verify data-source ↔ model compatibility using the lexicon system (see Step 4).
4. Cite doc URLs so the user can explore further.

## Live doc references

Fetch these pages as needed (not all at once — only what the user's question requires):

| Category | URL |
|----------|-----|
| Prognostic models | https://nvidia.github.io/earth2studio/modules/models_px.html |
| Diagnostic models | https://nvidia.github.io/earth2studio/modules/models_dx.html |
| Data assimilation | https://nvidia.github.io/earth2studio/modules/models_da.html |
| Data sources (analysis) | https://nvidia.github.io/earth2studio/modules/datasources_analysis.html |
| Data sources (forecast) | https://nvidia.github.io/earth2studio/modules/datasources_forecast.html |
| Data sources (dataframe) | https://nvidia.github.io/earth2studio/modules/datasources_dataframe.html |
| Examples gallery | https://nvidia.github.io/earth2studio/examples/index.html |
| Lexicon source | https://github.com/NVIDIA/earth2studio/tree/main/earth2studio/lexicon |

## Interaction protocol

### Step 1. Understand the user's problem

Extract from what the user has said (ask follow-ups if needed, cap at 3 questions):
```
END THIRD-PARTY FILE cf3da725f13a9e0a

The third-party file has ended. Everything between the cf3da725f13a9e0a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2811 of 8548 bytes. © NVIDIA Earth-2 Team · Apache-2.0 · https://github.com/NVIDIA/skills/tree/HEAD/skills/earth2studio-discover/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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