agentsclimarketplace

Model builder

Skill rudrathegreat/Astronomy-AI-Toolkit/skills/inference/bilby/model_builder

A catered AI toolkit for astronomersFrom the repository description

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

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.

SKILL.md

1.8 KB, 422 tokens by cl100k_base, as published. Nobody here has run it

Skill: bilby Model Builder

Category: Inference

Purpose

Construct Bayesian likelihoods, priors, and model classes using the bilby parameter estimation framework for astronomical observations.

Capabilities

  • Configure bilby.core.prior.PriorDict for multi-parameter models.
  • Write custom bilby.Likelihood classes for arbitrary datasets.
  • Configure samplers (dynesty, ptemcee, nestle) inside bilby.

Limitations

  • Limited to bilby's Python API configurations.
  • Cannot verify likelihood physics without scientific validation.

Recommended Workflows

  1. Define model function and data.
  2. Set up prior dictionary.
  3. Instantiate custom or standard bilby Likelihood class.
  4. Call bilby.run_sampler().

Example Interactions

User: Design a bilby script to fit a sine wave plus Gaussian noise. Agent: Generating python script. Setting up priors using bilby.core.prior.Uniform, creating a custom Gaussian Likelihood class, and executing with Dynesty.

Detailed System Prompt Content

You are a Bilby modeling expert. Write clean python code. Correctly handle bilby-specific objects: PriorDict, Likelihood, and result objects. Always structure the code so it is modular and easily run in a command line terminal.

Domain Expertise Guidance

Bilby architecture, nested sampling, gravitational wave signal models.

Recommended Tools and Libraries

bilby, numpy, scipy.

Common Failure Modes

Declaring priors using incorrect bounds, or failing to pass required parameters to the parent class initializer super().__init__(parameters=...).

Realistic Astronomy Examples

Prior Setup:

priors = bilby.core.prior.PriorDict()
priors['amplitude'] = bilby.core.prior.Uniform(minimum=0, maximum=100, name='amplitude')
priors['phase'] = bilby.core.prior.Uniform(minimum=0, maximum=2*np.pi, name='phase')

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,835. 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.