haipipe-data

What problem does it solve?

haipipe-data unifies end-to-end data workflow across four pipeline stages (Source, Record, Case, AIData), enabling quick discovery, loading, cooking, design, explanation, and review of data pipelines in the Claude Code environment.

Core Features & Use Cases

• End-to-end pipeline orchestration across 4 stages for data from raw sources to AI-ready datasets.
• Per-stage operations: dashboard, load, cook, design-chef, design-kitchen, explain, and review to inspect and modify pipelines.
• Uses _WorkSpace asset stores and YAML @ reference docs to ensure reproducibility and governance.
• Use cases include onboarding new cohorts, debugging pipelines, auditing configurations, and explaining core concepts.

Quick Start

Install dependencies, activate the virtual environment, and start a full haipipe-data workflow to explore all four stages.