analysis-refactor

What problem does it solve?

This skill provides a structured blueprint to transform a sprawling, ad-hoc data analysis script into a stable, five-layer modular architecture (constants → data loading → atomic functions → output functions → orchestrator run_one) to improve maintainability, reuse, and robustness.

Core Features & Use Cases

• Phase-driven refactoring to isolate constants, data loading, and computation, enabling predictable, auditable workflows.
• Pure, well-scoped functions with clear inputs and outputs; easier testing and reuse.
• Central orchestration via run_one that handles per-pair iteration, error handling, and consistent outputs.
• Clear separation of concerns (loading, processing, output) and deterministic results suitable for extension and testing.
• Guidance for retrofit-testing with /retrofit-tests to validate extracted components.

Quick Start

Begin by mapping your target script to the five-layer structure and use run_one to orchestrate per-pair computations.