Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL
All skills

earth2studio-install

Give exact uv or pip commands to install Earth2Studio and the model extras you choose.

  • Part of NVIDIA/skills
  • 1.9k installs
  • Machine Learning · Model research

When to use it

You have a GPU machine and a Python project but haven't installed Earth2Studio yet, or you're unsure which model extras like aifs or graphcast to add.

For example

You say

Use the earth2studio-install skill to set up Earth2Studio in a new uv project on Python 3.13 with the aifs and graphcast forecasting models.

You get
  • uv install commands
  • extra selection guidance
  • import version check

How it works

  • Fetches the live install docs first, since version tags and extra names change between releases.
  • Flags slow builds such as flash-attention and torch-harmonics that can take 10-30+ minutes.
  • Offers cache environment variables like EARTH2STUDIO_CACHE only when relevant.

Before installing

Needs Python 3.10+ (3.13 recommended), a CUDA-capable GPU with compatible drivers for GPU extras, and uv or pip; the assistant never runs installs itself, so you must run the commands.