Alphaearth Foundations Core Agent Skill
>- Core information for AlphaEarth Foundations Satellite Embeddings in Google Earth Engine (GEE).
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/google/earthengine-community --skill alphaearth_foundations_coreThe instruction itself
2 sections, as written by the authorThe Google Satellite Embedding dataset provides 64-dimensional geospatial
embeddings representing the semantic characteristics of Earth's surface at
10-meter resolution.
Specifications
- Dataset ID:
GOOGLE/SATELLITE_EMBEDDING/V1/ANNUAL - Bands: 64-dimensional float embeddings, named
A00throughA63. - Unit-Vector Guarantee: The bands are pre-normalized unit vectors (values
in range [-1, 1]).
See the catalog page for more details:
Satellite Embedding V1 (Annual)
Quantization & De-quantization (Under the Hood)
To store global high-dimensional embeddings efficiently, the dataset is internally quantized to 8-bit signed integers.
If you are accessing raw signed 8-bit integers in the raw collection
GOOGLE/SATELLITE_EMBEDDING/V1/ANNUAL_RAW or direct from the GCS bucket
gs://alphaearth_foundations/satellite_embedding/v1/annual/, the non-linear
de-quantization mapping used to reconstruct the native float values is:
$$v_{de\_quant} = \text{sign}(v_{raw}) \cdot \left(\frac{v_{raw}}{127.5}\right)^2$$
> [!NOTE] If reading raw COGs from the GCS bucket, mask the reserved no-data
> value -128 before applying this formula; otherwise it dequantizes to a value
> outside the valid [-1, 1] range.
def de_quantize(raw_image):
# Mask the reserved no-data value -128 before de-quantizing
raw_image = raw_image.updateMask(raw_image.neq(-128))
return raw_image.float() \
.divide(127.5) \
.pow(2) \
.multiply(raw_image.signum())
Other skills for the same job
different authors, same section of the catalogue
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.
Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
How to use it
Take google/alphaearth_foundations_core from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.