0D

0nicell/data-deletion-skill

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

25 stars Качество 50 Тренд 19NOASSERTION

A Claude skill for running structured personal-data erasure campaigns — 330 data brokers, OSINT tools and breach-search engines with verified privacy contacts, request templates for 13 privacy...

Обзор

Ships a registry of 330 organisations with verified privacy contacts, request templates for 13 privacy regimes, and escalation paths to 21 regulators. Built from a real ten-week campaign, not from a blog post about one. Ask someone where their personal data is and they will name a breach site or two. In the campaign this skill was built from, breach-search engines turned out to be the most visible exposure and one of the smallest categories. Sixty-nine organisations were B2B contact databases — legitimate, well-funded companies selling the subject's name and address per record. Twenty-eight were ad-tech platforms holding hashed identifiers and inferred segments. Most of the target list was discovered mid-campaign by asking one controller who it had shared data with, then following that thread. Removing yourself is not hard because the law is weak.

README

Показан фрагмент оригинального README. Открыть оригинал.

Data Deletion Skill

A Claude skill for running a structured personal-data erasure campaign against the commercial data-harvesting ecosystem. Ships a registry of 330 organisations with verified privacy contacts, request templates for 13 privacy regimes, and escalation paths to 21 regulators.

Built from a real ten-week campaign, not from a blog post about one.


The problem

Ask someone where their personal data is and they will name a breach site or two. In the campaign this skill was built from, breach-search engines turned out to be the most visible exposure and one of the smallest categories. Sixty-nine organisations were B2B contact databases — legitimate, well-funded companies selling the subject’s name and address per record. Twenty-eight were ad-tech platforms holding hashed identifiers and inferred segments. Most of the target list was discovered mid-campaign by asking one controller who it had shared data with, then following that thread.

Removing yourself is not hard because the law is weak. It is hard because it is 330 separate pieces of admin, each requiring a working contact address that is probably not the one on the privacy page, a legal basis matched to your jurisdiction, and a follow-up thirty days later that nobody remembers to send.

This skill is that admin, packaged.

What’s in it

SKILL.md The skill: an eight-step campaign process Claude follows
references/site-registry.md 330 organisations, nine categories, verified privacy contacts and recorded outcomes
references/site-registry.csv Same data, machine-readable
references/privacy-laws.md 13 regimes — article, deadline, right strength, regulator
references/templates-email.md Request bodies per regime, per site-category, plus chat / form / DM short forms
references/escalation.md Reply classification, rebuttals, follow-ups, 21 regulator complaint routes
references/troubleshooting.md Bounces, CAPTCHAs, geo-blocks, the From:-address trap, automation failures
references/playbook.md The campaign as a ten-week schedule with wave sizing
assets/tracker-template.md Tracker format
Открыть полный README на GitHub

Рекомендуемые инструменты

Попробуйте другой запрос или уберите фильтр.

Установка

npx skillfish add 0nicell/data-deletion-skill
Новичок в MCP? Начните с руководства на mcpskill.org →