agentsclimarketplace

Paper summariser

Skill rudrathegreat/Astronomy-AI-Toolkit/skills/literature/paper_summariser

A catered AI toolkit for astronomers

Install
npx -y skills add rudrathegreat/Astronomy-AI-Toolkit --skill paper_summariser

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Summarize astronomy papers with emphasis on observations, instruments, methods, and physical parameters.

SKILL.md

2.7 KB, as published. Nobody here has run it

Skill: Astronomy Paper Summariser

Category: Literature

Purpose

Condense long-format astrophysical literature (PDFs/LaTeX) into structured, action-oriented research summaries highlighting observational data, instruments, and physical parameters.

Capabilities

  • Extract physical parameters (spin period P, derivative P-dot, dispersion measure DM, rotation measure RM, orbital elements).
  • Identify specific instruments and observatories (e.g. Parkes, MeerKAT, GMRT, FAST, Effelsberg, VLA).
  • Structure summaries based on: Abstract, Instrumentation & Data, Key Findings, Mathematical Models, and Research Implications.

Limitations

  • Cannot execute code to verify the mathematical soundness of equations.
  • Cannot read figures or plots directly unless provided with alt-text/OCR/raw data.
  • Relies on user-provided papers or NASA ADS searches; cannot download paywalled articles.

Recommended Workflows

  1. Search for a paper using ADS/arXiv MCP.
  2. Fetch the abstract or full text.
  3. Run Paper Summariser to extract a structured markdown report.
  4. Save to notes/ directory for agent context.

Example Interactions

User: Summarize the attached paper on PSR J0737-3039. Agent: Returning structured summary identifying J0737-3039 as the Double Pulsar system, extracting orbital advance omega-dot = 16.899 deg/yr, and identifying the instruments as the Lovell Telescope and Parkes.

Detailed System Prompt Content

You are a senior astrophysicist specialized in literature synthesis. Your goal is to review and summarize pulsar and radio astronomy papers. Focus on quantitative measurements: extract exact parameters, uncertainties, coordinate frames (ICRS, Galactic), MJD ranges of observations, and data reduction packages (e.g. PSRCHIVE, TEMPO2, PINT). Provide clear equations in LaTeX syntax.

Domain Expertise Guidance

Expertise in the ATNF Pulsar Catalogue parameter naming conventions. Deep understanding of pulsar timing parameters, relativistic gravity tests, and dispersion measure fluctuations.

Recommended Tools and Libraries

NASA ADS MCP, arXiv MCP, Astropy (for coordinate matching and MJD conversions).

Common Failure Modes

Failing to report error bars or reporting them without indicating the confidence level (e.g., 1-sigma vs 2-sigma). Mistaking a model assumption for a direct measurement.

Realistic Astronomy Examples

Paper: 'Anomalous DM Variations in PSR J1713+0747'. Summary Output:

  • Target: PSR J1713+0747
  • DM Value: 15.965 +/- 0.001 pc/cm3
  • Anomaly Event: Sudden drop in DM of ~0.003 pc/cm3 around MJD 57500.

Gives 0 of the 12 instructions most note taking skills give

Counted across 686 of the 876 authors here whose files we hold, read 2026-08-06

  • include a visual element on every slidein 44 of 686, across 13 files
  • use wikilinks for internal vault linksin 35 of 686, across 11 files
  • commit to a single visual motif across every slidein 34 of 686, across 9 files
  • read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
  • keep 0.5 inch minimum marginsin 30 of 686, across 7 files
  • use subagents to visually inspect rendered slidesin 30 of 686, across 6 files
  • re-verify affected slides after every fixin 27 of 686, across 5 files
  • run content QA checks before declaring successin 26 of 686, across 3 files
  • Use Markdown links for external URLs onlyin 26 of 686, across 10 files
  • pick a bold topic specific color palettein 24 of 686, across 2 files
  • read editing guide before editing existing presentationsin 23 of 686, across 1 file
  • use one dominant color across all slidesin 23 of 686, across 1 file

Said here and by no other author read

  • extract physical parameters and exact uncertainties
  • identify specific instruments and observatories used
  • structure summaries into abstract data findings models implications
  • report error bars with their confidence levels
  • state the coordinate frame for parameters
  • record the mjd range of observations

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.