data-layer-architecture

Official

Secure extraction history with Bronze-Gold layers

Authorsage-base
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill defines a robust two-layer architecture (Bronze extraction logs and Gold confirmed data) to preserve AI extraction history, enable auditability, and protect human corrections during data curation.

Core Features & Use Cases

  • Immutable Bronze layer: Append-only ExtractionLog records that capture AI extractions for traceability and model improvement.
  • Mutable Gold layer with protection: Gold entities update only when is_manually_verified is false; manual verification preserves human-corrected data.
  • End-to-end data governance: Link between extraction logs and gold data enables auditing, rollback, and compliant data curation.

Quick Start

Initialize a two-layer extraction system by logging a sample extraction to ExtractionLog, then show how Gold is updated when is_manually_verified is false and preserved when true.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: data-layer-architecture
Download link: https://github.com/sage-base/sagebase/archive/main.zip#data-layer-architecture

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 223,000+ vetted skills library on demand.