Astropy Astronomy Toolkit
Helps Claude write and debug Astropy code for units, coordinates, FITS I/O, tables, time scales, WCS and cosmology.
Dev & CodingIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026
What it does
Gives Claude an accurate, up-to-date map of Astropy, the core Python package for astronomy.
- Units & quantities (
astropy.units): conversions, arithmetic with units, spectral/Doppler/parallax equivalencies, logarithmic units - Coordinates (
astropy.coordinates): ICRS/Galactic/FK5/AltAz transforms, separations, proper motions, catalog matching - FITS (
astropy.io.fits): HDU access, header editing, multi-extension files, memory mapping, remote/S3 reads - Tables (
astropy.table): FITS/CSV/HDF5/VOTable I/O, joins, grouping, masking, unit-aware QTable - Time (
astropy.time): UTC/TAI/TT/TDB scales, JD/MJD formats, sidereal time, barycentric corrections - WCS, cosmology, constants, convolution, statistics: pixel↔world transforms, luminosity distance, lookback time, sigma clipping
Per-module reference files keep the main skill lean, and the doc flags Astropy 7.2 behavior plus deprecations removed in 8.0.
Who it's for
- Astronomers, astrophysics grad students, and observatory data analysts
- Data scientists handling FITS imagery or source catalogs
- Developers new to Astropy who want idiomatic patterns (always attach units, use context managers, vectorize)
Example uses
- Coordinate work: "Convert this RA/Dec list to Galactic coordinates and compute Alt/Az for a site at lat 40°, lon -120° on 2023-06-15."
- Catalog cross-match: "Match catalog1.fits to catalog2.fits within 1 arcsec and write out the matched rows."
- Cosmology table: "Using Planck18, tabulate luminosity distance and lookback time for z = 0.1–3 and plot the result."
· · · Install guide · · ·
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/astropy folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/astropy/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/astropy ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and confirm Claude Code is installed (
claude --version). - Clone the repository:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy just this skill:
cp -r scientific-agent-skills/skills/astropy ~/.claude/skills/ - Install Astropy in a virtual environment (Python 3.11+ required):
uv pip install "astropy==7.2.0", or"astropy[recommended]==7.2.0"for plotting extras. - Restart Claude Code and try a prompt like "Use astropy to convert these ICRS coordinates to Galactic."
- Note that object name resolution, site lookups, remote FITS reads and IERS updates require network access — avoid sending sensitive target names or file paths to external services.
View source on GitHub ↗License: MIT