Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/astrophysics-data-guide
Astronomical data processing with Astropy, FITS files, and sky surveys
Passed 14 of 22 test cases with the skill, and 7 of 22 without it.
and 5 more in the full report
7 fixed7 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Calculate the instrumental magnitude for a detected star given net background-subtracted flux count of 1500.0 phot-counts.
| Checked | Without skill | With skill |
|---|---|---|
| Computes magnitude using formula -2.5 * log10(net_flux). | Passed | Passed |
| Returns magnitude rounded to 4 decimal places. | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for processing and analyzing astronomical data using standard astrophysics tools. Covers FITS file handling, coordinate transformations, photometric analysis, spectral analysis, catalog cross-matching, and accessing major sky survey archives.
FITS (Flexible Image Transport System) is the standard data format in astronomy:
from astropy.io import fits
import numpy as np
def inspect_fits(filepath: str) -> dict:
"""
Inspect the structure of a FITS file.
Returns information about each HDU (Header/Data Unit).
"""
with fits.open(filepath) as hdul:
info = []
for i, hdu in enumerate(hdul):
entry = {
"index": i,
"name": hdu.name,
"type": type(hdu).__name__,
}
if hdu.data is not None:
entry["shape"] = hdu.data.shape
entry["dtype"] = str(hdu.data.dtype)
if hasattr(hdu, "columns") and hdu.columns is not None:
entry["columns"] = [c.name for c in hdu.columns]
info.append(entry)
return {"filename": filepath, "n_hdus": len(hdul), "hdus": info}
def read_fits_image(filepath: str, hdu_index: int = 0) -> tuple:
"""Read a FITS image and its WCS (World Coordinate System)."""
from astropy.wcs import WCS
with fits.open(filepath) as hdul:
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.