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.
Also in this pack
- accelerated-computing-cudf3.2kGuides GPU DataFrame work with cuDF, including pandas acceleration, joins, groupby, file I/O and multi-GPU jobs.
- cuopt-developer2.8kModifies, builds, tests, and debugs NVIDIA cuOpt source code and prepares contributions.
- cuopt-install2.6kInstalls cuOpt for Python, C, or server via pip, conda, or Docker and verifies it works.
- data-designer2.6kGenerates a synthetic dataset from your description of the data you need.