Skip to content
Get packs

Astropy Astronomy Toolkit

Lets an agent write and debug astronomy code using Astropy for units, coordinates, FITS, tables, time and cosmology

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
9 files

What it does

Astropy is the standard Python library for astronomy. With this skill installed, the agent knows Astropy's conventions and common pitfalls, so when you ask for help with astronomical data it writes correct code for converting units, transforming sky coordinates, reading FITS files and catalogs, handling precise time scales, WCS pixel-to-sky mapping, and cosmology calculations. It also points to detailed reference notes bundled with the skill rather than relying on memory.

Great for

  • Astronomy students learning to handle telescope data in Python
  • Researchers writing or debugging Astropy analysis scripts
  • Developers building astronomy data pipelines who want fewer API mistakes

Skip it if

  • Non-astronomy data work, where the astronomy-specific APIs add no value
  • Users on Python below 3.11 or without NumPy 2, since the skill states these requirements and code will fail otherwise
  • Scientific claims that must be published without independent checking, because generated code can still contain errors the user has to verify

Try asking

  • “Convert a list of RA/Dec positions to Galactic coordinates and plot them”
  • “Compute the luminosity distance for redshift 1.0 using the Planck18 cosmology”
  • “Read a FITS catalog into a table, filter rows by magnitude, and cross-match to another catalog”
  • “Debug why my WCS pixel-to-sky conversion returns offset positions”
Step-by-step guide: how to use Astropy Astronomy ToolkitInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 9 original files, the MIT licence and an attribution note.

    astropy.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip astropy.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip astropy.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent your actual file names and column names so it writes code that matches your data rather than illustrative placeholders.
  • Check results on a small known example (for instance a known object's coordinates) before running on a full dataset.
  • Network features such as object name lookups, remote FITS reads and IERS updates need internet access; disable them if your environment must stay offline.

What's inside

  • references/coordinates.md
  • references/cosmology.md
  • references/fits.md
  • references/review.md
  • references/tables.md
  • references/time.md
  • references/units.md
  • references/wcs_and_other_modules.md
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.