One-click install
npx skills add https://github.com/statsclaw/statsclaw --skill privacy-scrub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: privacy-scrub
Source: https://github.com/statsclaw/statsclaw/tree/main/skills/privacy-scrub
Command: npx skills add https://github.com/statsclaw/statsclaw --skill privacy-scrub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Knowledge entries contributed to the shared brain risk exposing personally identifiable information about source projects, users, or organizations, making them unsafe for reuse by other teams and violating the framework's privacy requirements.

Core Features & Use Cases

  • Mandatory Scrub Categories: Defines clear rules for stripping identifiers, file paths, code references, and dataset metadata from knowledge entries.
  • Verification Protocol: Provides a step-by-step checklist for reviewer agents to confirm PII removal before contribution.
  • CI Alignment: Matches automated PII scanning rules used in the brain-seedbank repository's validation workflow.
  • Use Case: When a distiller agent extracts reusable knowledge from a statistical package development workflow, this skill ensures all project-specific identifying information is genericized before the entry is proposed for the shared brain.

Quick Start

Use the privacy-scrub skill to genericize all identifying information in the extracted knowledge entry before proposing it for contribution to the shared brain.

Frequently Asked Questions about privacy-scrub

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

FAQPage Schema
How do I remove personally identifiable information from knowledge entries before sharing?

To remove PII from knowledge entries, apply strict genericization rules to strip identifiers, file paths, code references, and dataset metadata before proposing contributions to a shared brain repository.

What is genericization for safe knowledge contribution in statistical workflows?

Genericization for safe knowledge contribution is the process of replacing project-specific identifiers and metadata with generic terms so statistical workflow knowledge can be reused without privacy violations.

How do I verify PII removal before contributing to a shared brain repository?

Verify PII removal by running a step-by-step reviewer agent checklist that confirms all identifiers, file paths, and code references are genericized before the knowledge entry submission.

Does the privacy-scrub genericization process align with automated CI scanning checks?

The genericization process aligns with automated CI scanning checks used in the brain-seedbank repository's validation workflow to enforce PII removal during continuous integration.

Can I use this scrubbing protocol for knowledge extracted by a distiller agent?

You can use this scrubbing protocol when a distiller agent extracts reusable knowledge from statistical package development workflows, ensuring all identifying information is genericized before submission.

What limitations exist when stripping dataset metadata from shared knowledge entries?

Limitations include the strict scope of mandatory scrub categories, meaning you must carefully genericize all dataset metadata, code references, and file paths to avoid violating framework privacy requirements.