Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/satellite-remote-sensing
Satellite imagery analysis and remote sensing for earth science research
Passed 22 of 24 test cases with the skill, and 19 of 24 without it.
3 fixed19 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
For daily global vegetation monitoring at coarse spatial resolution, which NASA mission and instrument provides 36 spectral bands at 250m to 1km resolution, and from which DAAC repository can it be downloaded?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies MODIS as the satellite sensor | Passed | Passed |
| Names NASA LAADS DAAC as the access archive | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for processing and analyzing satellite imagery for earth science research. Covers data acquisition from major satellite platforms, preprocessing workflows, spectral index computation, land cover classification, and change detection using Python geospatial tools.
| Mission | Operator | Resolution | Revisit | Key Bands | Access |
|---|---|---|---|---|---|
| Landsat 8/9 | USGS/NASA | 30m (MS), 15m (pan) | 16 days | 11 bands, OLI+TIRS | Free (USGS EarthExplorer) |
| Sentinel-2 | ESA | 10m-60m | 5 days | 13 bands, MSI | Free (Copernicus Open Access Hub) |
| MODIS | NASA | 250m-1km | 1-2 days | 36 bands | Free (NASA LAADS DAAC) |
| Sentinel-1 | ESA | 5-20m | 6 days | C-band SAR | Free (Copernicus) |
| GOES-16/17 | NOAA | 0.5-2km | 5-15 min | 16 bands, ABI | Free (NOAA CLASS) |
import planetary_computer
import pystac_client
import rioxarray
# Search Sentinel-2 imagery via Microsoft Planetary Computer
catalog = pystac_client.Client.open(
"https://planetarycomputer.microsoft.com/api/stac/v1",
modifier=planetary_computer.sign_inplace,
)
# Search for cloud-free imagery over a region
search = catalog.search(
collections=["sentinel-2-l2a"],
bbox=[11.0, 46.0, 12.0, 47.0], # Tyrol, Austria
datetime="2025-06-01/2025-08-31",
query={"eo:cloud_cover": {"lt": 10}},
)
items = search.item_collection()
print(f"Found {len(items)} scenes with <10% cloud cover")
test cases passed, vs 19 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.