amey-thakur/ai-skills/data-minimization
Claude Code and agent skill by amey-thakur/ai-skills
- community
Checking that the SKILL.md file is still in the repository.
Collect and keep only the personal data a feature actually needs, so exposure, cost, and compliance burden all shrink at once. Use when designing a form, an event schema, a log line, or any system that touches personal data.
Install
npx vskill@latest install amey-thakur/ai-skills/data-minimizationSKILL.md
The same SKILL.md was published earlier as amey-thakur/ai-skills/data-minimization.
Data minimization
Every field you collect is a field you must secure, justify, retain, delete, and disclose. Minimization is the cheapest privacy control there is, because data you never held cannot leak, cannot be subpoenaed, and never appears in a breach notice.
Method
- Tie every field to a stated purpose. Before a field enters a
form, an event, or a log, name the decision it supports. Fields kept because they might be useful later are the ones that show up in incidents with nobody able to explain why they existed.
- Prefer derived over raw. Store an age band rather than a birth
date, a region rather than a precise location, a hash rather than the identifier itself when you only need to match. The narrower form answers the same question with less to lose.
- Separate identity from behaviour. Keep identifiers in one place
and events in another, joined by a surrogate key. Analytics that never carries names is analytics that cannot leak them (see data-anonymization).
- Watch the accidental collectors. Logs, crash reports, analytics
payloads, and support screenshots collect personal data nobody planned for. Redact at the point of capture rather than promising to clean it up later (see structured-logging).
- Set an expiry with the field, not afterwards. Deciding how long
something lives at the moment you add it is far easier than reconstructing a retention policy for a table that has grown for three years (see right-to-erasure).
- Re-check on every schema change. New fields arrive with new
features and rarely get the same scrutiny as the original design, so make a quick purpose check part of review (see privacy-by-design).
Boundaries
- Minimization reduces exposure; it does not replace access control or
encryption for what you do keep (see authz-design, data-encryption).
- Some data is legally required to retain, and minimizing it is not
yours to decide (see data-classification, vendor-data-processing).
- Aggregation is not automatically anonymous; small groups remain
identifiable (see data-anonymization).
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/data-privacy/data-minimization/SKILL.md
Popularity
- Repository stars
- 10
- Repository forks
- 2
- 7-day trend score
- 17
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/amey-thakur/ai-skills/data-minimization)