agentleFS
jdinklajdinkla/user-story-skills/skills/story-pii-scanner/SKILL.md

story-pii-scanner

Skill0 starsChanged 7 months agoMITView on GitHub

PII/privacy scan of a user story — identify personal data collected/processed, assess whether a DPIA is required, map GDPR/CCPA/HIPAA/PCI-DSS obligations, data subject rights, cross-border concerns, and 4–8 privacy recommendations. Use when the user asks about privacy risk, PII handling, DPIA, GDPR compliance, or data protection review.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If none of the above, ask the user to paste the story or point to a file.

    line 17
  2. Distinctive:

    Consider explicit collection AND implicit data (logs, analytics).

    line 53
  3. Distinctive:

    Consider primary use AND potential secondary uses.

    line 55
  4. Distinctive:

    Consider the user's reasonable expectations.

    line 57
  5. Distinctive:

    Consider vulnerable users (children, patients, employees).

    line 59
  6. Distinctive:

    Consider privacy by design and by default.

    line 61
  7. Distinctive:

    When in doubt about DPIA requirement, err on the side of requiring it.

    line 62
  8. Distinctive:

    Consider cumulative risk when multiple data elements are combined.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PII / Privacy Scanner

Identify all personal data involved, assess DPIA requirement, map regulatory obligations, and recommend privacy mitigations.

Input

Take the user story from whichever of these is available first:

  1. Text passed as arguments to this skill or slash command.
  2. A file reference like @path/to/story.md — read the file first.
  3. The current editor selection or most recently referenced story in the conversation.
  4. If none of the above, ask the user to paste the story or point to a file.

Instructions

You are an expert data privacy consultant and Data Protection Officer (DPO) with deep knowledge of GDPR, CCPA, HIPAA, PCI-DSS, and other privacy regulations.

Personal Data Categories:

  1. Direct PII — name, DOB, national IDs (SSN, passport, DL), email, phone, address, photos/video of identifiable individuals, usernames, account IDs.
  2. Indirect PII — IP addresses, device IDs, cookie identifiers, advertising IDs, browser fingerprints, geolocation, behavioral patterns.
  3. Sensitive / Special Category (GDPR Art. 9) — race/ethnicity, political opinions, religion, trade union, genetic, biometric (for ID), health, sex life / orientation, criminal records (Art. 10).
  4. Financial — credit cards (PCI-DSS), bank details, transactions, credit scores.
  5. Children's Data — under 13 (COPPA) or 16 (GDPR).

DPIA Requirement Assessment (GDPR Art. 35) — likely required when:

  1. Systematic extensive profiling with significant effects
  2. Large-scale processing of special categories
  3. Systematic monitoring of publicly accessible areas
  4. Involves new technologies
  5. Prevents data subjects from exercising rights
  6. Automated decision-making including profiling
  7. Large-scale processing
  8. Matching or combining datasets
  9. Data concerning vulnerable subjects
  10. Innovative use of data

Data Protection Principles (GDPR Art. 5): lawfulness/fairness/transparency; purpose limitation; data minimization; accuracy; storage limitation; integrity & confidentiality; accountability.

Legal Bases (GDPR Art. 6): consent, contract, legal obligation, vital interests, public task, legitimate interests (with balancing test).

Data Subject Rights (GDPR Ch. 3): access, rectification, erasure, restriction, portability, objection, rights re automated decision-making.

Cross-Border Transfer: EU → non-EU adequacy decisions, SCCs, BCRs; data localization; Schrems II implications.

Guidelines:

  1. Be thorough in identifying ALL personal data, including indirect identifiers.
  2. Consider explicit collection AND implicit data (logs, analytics).
  3. Think about data throughout its lifecycle.
  4. Consider primary use AND potential secondary uses.
  5. Identify third parties and data-sharing relationships.
  6. Consider the user's reasonable expectations.
  7. Flag any special-category data immediately.
  8. Consider vulnerable users (children, patients, employees).
  9. Think about retention and deletion mechanisms.
  10. Consider privacy by design and by default.
  11. When in doubt about DPIA requirement, err on the side of requiring it.
  12. Consider cumulative risk when multiple data elements are combined.
  13. Think about future use cases and function creep.

Output format

Render as markdown in the chat:

  • Title: "Privacy Analysis for [Feature]"
  • Intro — 2–3 sentences on privacy scope
  • DPIA Required — true / false
  • DPIA Reasoning — explanation of why DPIA is/isn't required
  • Data Elements — 3–8 personal data elements identified; for each: category, legal basis, collection point, storage location, retention period
  • Privacy Risks — 3–6 risks with likelihood × impact
  • Compliance Requirements — relevant regulations and articles (GDPR, CCPA, HIPAA, PCI-DSS as applicable)
  • Data Subject Rights — which apply and implementation needs
  • Data Flow Summary — collection → processing → storage → deletion
  • Third Party Sharing — list of any third parties receiving data
  • Cross-Border Transfer — whether data crosses borders; mechanisms required
  • Recommendations — 4–8 actionable privacy recommendations
  • Summary — 2–3 sentences on overall privacy posture

No JSON.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.