amortized-workflow

Official

Guarded end-to-end Bayesian SBI workflow.

AuthorLearning-Bayesian-Statistics
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Provides a structured, guarded end-to-end workflow for performing amortized Bayesian inference with BayesFlow, enforcing best practices and guardrails to improve reliability and reproducibility.

Core Features & Use Cases

  • Enforces the complete amortized Bayesian workflow: formulate the generative model, configure simulator regimes (offline, online, or disk training), choose architecture, build the adapter, train, diagnose, perform PPCs, and generate reports.
  • Provides strong guardrails and conventions (validation data, diagnostics, reporting) to ensure repeatable analyses across projects and datasets.
  • Integrates with BayesFlow networks (SetTransformer, DiffusionModel, FlowMatching, etc.) and supports both vector and structured data (sets, time series, images) via the conditioning logic.
  • Works with compatible agents and supports multiple deployment modalities (Claude Code, Kimi Code, Cursor, Gemini CLI) per the Agent Skills spec.

Quick Start

Install BayesFlow and run the provided workflow to train an amortized estimator with offline training.

Dependency Matrix

Required Modules

pandas

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: amortized-workflow
Download link: https://github.com/Learning-Bayesian-Statistics/baygent-skills/archive/main.zip#amortized-workflow

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.