tessera

Retrieve and transform TESSERA satellite embedding tiles into point samples or dense mosaics.

66|10|Updated Mar 19, 2026

Search Tags:#tessera #satellite embeddings #geospatial ml #parquet registry #zarr export #bbox download

Ready to run

npx skills add https://github.com/isaaccorley/geospatial-skills --skill tessera

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tessera
Source: https://github.com/isaaccorley/geospatial-skills/tree/main/plugins/tessera/skills/tessera
Command: npx skills add https://github.com/isaaccorley/geospatial-skills --skill tessera

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

TESSERA embedding workflows become slow and error-prone when you need to discover coverage, download only the required tiles, and turn them into point samples or dense raster mosaics for downstream geospatial ML.

Core Features & Use Cases

Point sampling: sample embeddings at (lon, lat) locations to get an (N, 128) float32 array with NaNs for missing points, ideal for labeled site extraction and sparse classification.
Dense mosaics: fetch mosaics for a bbox to get a (H, W, 128) float32 array for wall-to-wall raster analysis like spatial clustering or land cover classification.
Multi-language + output formats: use the geotessera CLI, Python, or R, and export to GeoTIFF, NPY, or Zarr with configurable bands and cache/registry behavior.

Quick Start

Use this skill to sample TESSERA embeddings at a list of longitude/latitude points with the geotessera Python library for a specified year.

Frequently Asked Questions about tessera

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I download TESSERA satellite embeddings for a specific bounding box?▼

Download TESSERA satellite embeddings for a specific bounding box by specifying the region and year to fetch dense mosaics as an (H, W, 128) float32 array. Export results directly to GeoTIFF, NPY, or Zarr formats.

What is the best way to sample satellite embeddings at specific latitude and longitude coordinates?▼

Sample satellite embeddings at specific latitude and longitude coordinates to retrieve an (N, 128) float32 array. Missing points are automatically filled with NaNs, making it ideal for labeled site extraction and sparse classification tasks.

Can I use the geotessera library to export geospatial ML embeddings to Zarr?▼

Yes, you can use the geotessera CLI, Python, or R libraries to export geospatial ML embeddings to Zarr. The process supports configurable bands, hash-verified cached registry access, and optional output formats including GeoTIFF and NPY.

Does the TESSERA embedding download process support coverage checking before fetching tiles?▼

Yes, coverage checking is supported before fetching TESSERA tiles. You can verify available data for a specified year and region file, ensuring hash-verified cached registry access prevents downloading unnecessary or missing tiles.

What output formats are available when creating dense mosaics from satellite embedding tiles?▼

Available output formats for dense mosaics from satellite embedding tiles include GeoTIFF, NPY, and Zarr. These formats support wall-to-wall raster analysis like spatial clustering and land cover classification with configurable bands.

Why do my point samples from TESSERA embeddings contain NaN values?▼

Point samples from TESSERA embeddings contain NaN values to represent missing data at requested (lon, lat) locations. This ensures the output (N, 128) float32 array maintains consistent dimensions for downstream sparse classification and labeled site extraction.