pymc

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

1.49x

Quality

83%

Does it follow best practices?

Impact

88%

1.49x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

46%

Air Quality Prediction with Bayesian Regression

Full Bayesian workflow

Criteria

Without context

With context

Predictor standardization

100%

Weakly informative priors

100%

HalfNormal for scale

100%

Named dims usage

100%

coords dict in model

100%

Prior predictive check

100%

Sampling parameters

100%

log_likelihood in idata

100%

random_seed set

100%

Diagnostics script used

100%

Posterior predictive check

100%

pm.Data for predictions

100%

Results saved as netcdf

100%

Predictions file created

100%

28%

Student Performance Modeling Across Schools

Hierarchical model non-centered parameterization

Criteria

Without context

With context

Non-centered parameterization

100%

pm.Deterministic for intercepts

100%

Hyperpriors defined

100%

HalfNormal for scale hyperprior

100%

coords and dims used

100%

Predictor standardization

100%

Diagnostic report script

100%

R-hat threshold 1.01

100%

ESS threshold 400

100%

Sampling parameters

100%

Results saved as netcdf

100%

65%

13%

Customer Purchase Rate Modeling: Selecting the Best Count Model

LOO model comparison and averaging

Criteria

Without context

With context

compare_models script used

check_loo_reliability used

100%

model_averaging used

log_likelihood in all models

100%

Δloo < 2 → prefer simpler

Pareto-k threshold 0.7

100%

NegativeBinomial model

100%

ZeroInflatedPoisson model

100%

Predictor standardization

100%

random_seed set

100%

Comparison report saved

100%

Sampling parameters

37%

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Air Quality Prediction with Bayesian Regression Student Performance Modeling Across Schools Customer Purchase Rate Modeling: Selecting the Best Count Model

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.