building-data-dictionary-with-consent-class

Build a consent-classified data dictionary with DSR scope and lawful basis.

2|Updated May 23, 2026
One-click install
npx skills add https://github.com/rocklambros/rcs --skill building-data-dictionary-with-consent-class
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: building-data-dictionary-with-consent-class
Source: https://github.com/rocklambros/rcs/tree/main/skills/ml-datasci/building-data-dictionary-with-consent-class
Command: npx skills add https://github.com/rocklambros/rcs --skill building-data-dictionary-with-consent-class

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps teams create a field-by-field data dictionary that captures both technical schema details and privacy-critical consent classification so they can answer data subject requests and pass privacy reviews with confidence.

Core Features & Use Cases

  • Per-field inventory: Documents name, type, nullability, semantic class, lawful basis, and sensitivity for each field in a dataset.
  • Consent classification: Distinguishes collected, inferred, derived, public, and synthetic fields so privacy scope is accurate.
  • DSR readiness: Maps access, portability, deletion, rectification, and propagation across downstream copies, embeddings, caches, and snapshots.
  • Use case: A SaaS team with user profiles, clickstream events, and model outputs can use this Skill to build a legally defensible inventory for GDPR and CCPA response workflows.

Quick Start

Ask Claude to inventory your existing schema and build a consent-classified data dictionary for your user-related tables, including DSR scope, lineage, and lawful basis.

Frequently Asked Questions about building-data-dictionary-with-consent-class

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a data dictionary for GDPR and CCPA compliance?

A privacy-aware data dictionary captures technical schema details and consent classifications like collected, inferred, and derived fields. It distinguishes public and synthetic data to ensure accurate privacy scope for user-related datasets across schemas and ML pipelines.

How do I map data subject request scope across downstream ML pipelines?

You map data subject request (DSR) scope by tagging access, portability, deletion, and rectification requirements per field. This propagates consent classes and lineage tracking across downstream copies, embeddings, caches, and snapshots within your ML pipelines.

Can I classify inferred and derived fields for HIPAA privacy reviews?

Any team managing user profiles, clickstream events, and model outputs can use this approach to build a legally defensible inventory. It suits SaaS environments needing to answer data subject requests and pass privacy reviews across complex schemas.

What is the best way to track lineage and orphan fields in a user data inventory?

The best way to track lineage and orphan fields is through per-field schema extraction combined with lineage propagation checks. This validates that every collected, inferred, or derived field in your tables has a documented source and lawful basis.