Provides a structure for developing Bayesian models and diagnostic workflows in Python.

Install

mkdir -p .claude/skills/pymc && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18166" && unzip -o skill.zip -d .claude/skills/pymc && rm skill.zip

Installs to .claude/skills/pymc

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Build Bayesian models and probabilistic analysis workflows.
59 chars · catalog descriptionno explicit “when” trigger
Intermediate

Key capabilities

  • Build Bayesian models for probabilistic analysis
  • Define priors for model parameters
  • Specify likelihood functions for observed data
  • Perform inference using `pm.sample`
  • Generate trace plots for visual diagnostics
  • Summarize model parameters and diagnostics

How it works

The skill uses PyMC to define a Bayesian model with priors and likelihood, then performs inference to generate a trace and provides diagnostic checks.

Inputs & outputs

You give it
Observed data and a defined PyMC model structure
You get back
Inference data (trace) and diagnostic plots/summaries

When to use pymc

  • Building probabilistic models
  • Quantifying uncertainty in data
  • Running Bayesian statistical inference

About this skill

pymc

Build Bayesian models and probabilistic analysis workflows.

When to use

When uncertainty quantification, prior knowledge incorporation, or small-data inference is needed.

Basic model structure

import pymc as pm
import numpy as np

with pm.Model() as model:
    # Priors
    mu = pm.Normal("mu", mu=0, sigma=10)
    sigma = pm.HalfNormal("sigma", sigma=1)

    # Likelihood
    obs = pm.Normal("obs", mu=mu, sigma=sigma, observed=data)

    # Inference
    trace = pm.sample(2000, return_inferencedata=True)

# Diagnostics
pm.plot_trace(trace)
pm.summary(trace)

Diagnostics checklist

  • R-hat < 1.01 for all parameters
  • Effective sample size (ESS) > 400
  • No divergences
  • Trace plots show good mixing

Source

Scientific Agent Skills (K-Dense-AI/scientific-agent-skills)

When not to use it

  • When uncertainty quantification is not needed
  • When prior knowledge incorporation is not needed
  • When small-data inference is not needed

Limitations

  • Requires `pymc` and `numpy` libraries
  • Focuses on basic model structure and diagnostics
  • Diagnostics checklist includes R-hat, Effective sample size, and trace plots

How it compares

This skill provides a structured approach to building and analyzing Bayesian models with built-in diagnostics, offering a systematic way to quantify uncertainty compared to traditional statistical methods.

Compared to similar skills

pymc side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pymc (this skill)027dNo flagsIntermediate
quant-analyst1032moNo flagsAdvanced
umap-learn61moReviewIntermediate
embedding-strategies82moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

quant-analyst

zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

103355

umap-learn

K-Dense-AI

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

6100

embedding-strategies

wshobson

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

890

building-automl-pipelines

jeremylongshore

Build automated machine learning pipelines, including feature engineering, model selection, and performance evaluation.

688

model-compare

rawwerks

Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.

783

matchms

davila7

Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.

674

Search skills

Search the agent skills registry