Skip to content
Agentmart
Submit a tool

privacy-compliance

Use this skill when implementing GDPR or CCPA compliance, designing consent management, conducting DPIAs, or managing data processing agreements.

Skill by mkurman

IndexedMIT★ 325
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mkurman-privacy-compliance

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use this skill when implementing GDPR or CCPA compliance, designing consent management, conducting DPIAs, or managing data processing agreements. Triggers on GDPR, CCPA, data privacy, consent management, DPIA, data subject rights, privacy policy, cookie consent, and any task requiring privacy regulation compliance or data protection design.

Use cases: design, data, security, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/privacy-compliance

What's inside

Skill name
privacy-compliance
Description
Use this skill when implementing GDPR or CCPA compliance, designing consent management, conducting DPIAs, or managing data processing agreements. Triggers on GDPR, CCPA, data privacy, consent management, DPIA, data subject rights, privacy policy, cookie consent, and any task requiring privacy regulation compliance or data protection design.
License
MIT
Instructions
384 lines in SKILL.md · view on GitHub

Files (4)

  • README.md
  • SKILL.md
  • evals.json
  • gdpr-ccpa-comparison.md · references/

SKILL.md (first lines)

## Key principles

1. **Privacy by design** - Build privacy controls into the architecture from day
   one. Data minimization, access controls, and audit logs are structural decisions,
   not features added after launch. Retrofitting is expensive and incomplete.

2. **Data minimization** - Collect only what you need, retain it only as long as
   necessary, and delete it on schedule. Every field in your database is a liability
   if you cannot justify its purpose and retention period.

3. **Lawful basis for processing** - Every processing activity must have a documented
   lawful basis (GDPR) or a disclosure obligation (CCPA). "We might need it someday"
   is not a lawful basis. Document the basis before you collect the data.

4. **Transparency** - Users must understand what data you collect, why, how long you
   keep it, and who you share it with. Privacy policies must be readable, not a legal
   wall. Consent must be informed to be valid.

5. **Accountability** - Maintain records of processing activities (RoPA), run DPIAs
   for high-risk processing, appoint a DPO when required, and respond to data subject
   requests within statutory deadlines. Compliance is a continuous process, not a
   one-time audit.

---

## Core concepts

### GDPR vs CCPA at a glance

| Dimension | GDPR (EU/EEA) | CCPA / CPRA (California) |
|---|---|---|
| Scope | Any org processing EU/EEA residents' data | Businesses meeting revenue/data thresholds serving CA residents |
| Legal basis required | Yes - 6 lawful bases | No explicit basis required; disclosure + opt-out |
| Consent standard | Freely given, specific, informed, unambiguous, withdrawable | Opt-out for sale/sharing; opt-in for sensitive data (CPRA) |
| Data subject rights | Access, rectification, erasure, portability, restriction, objection, no automated decision | Know, delete, correct, opt-out of sale/sharing, limit sensitive data use, non-discrimination |
| Response deadline | 30 days (extendable to 90 days) | 45 days (extendable to 90 days) |
| Breach notification | 72 hours to supervisory authority; notify individuals if high risk | Reasonable time; private right of action for breaches |
| Penalties | Up to 4% global annual turnover or €20M | Up to $7,500 per intentional violation |
| DPO required | For large-scale systematic processing or sensitive data | No equivalent role required |
| Cross-border transfers | SCCs, adequacy decisions, BCRs required | No equivalent mechanism required |

### Lawful bases for processing (GDPR Art. 6)

| Basis | When to use | Gotcha |
|---|---|---|
| Consent | Marketing, non-essential cookies, optional features | Must be withdrawable; withdrawal must be as easy as giving it |
| Contract | Processing necessary to fulfill a contract with the user | Can only cover what is genuinely necessary for the contract |
| Legal obligation | Tax records, fraud reporting mandated by law | Must be a specific law, not a vague compliance claim |
| Vital interests | Emergency medical situations | Rarely applicable outside health contexts |
| Public task | Government and public authority processing | Not applicable to most private organizations |
| Legitimate interests (LI) | Analytics, fraud prevention, direct marketing (with caveats) | Must pass LI Assessment (LIA) - user interests must not override yours |

### Data subject rights

| Right | GDPR | CCPA/CPRA | Implementation note |
|---|---|---|---|
| Right to know / access | Art. 15 | Yes | Export all personal data in a portable format |
| Right to rectification / correction | Art. 16 | CPRA only | Update incorrect data across all systems |
| Right to erasure ("right to be forgotten") | Art. 17 | Yes | Cascade deletes across primary store, replicas, backups, third-party processors |
| Right to portability | Art. 20 | Yes (categories + specific pieces) | Machine-readable format (JSON, CSV) |
| Right to restriction of processing | Art. 18 | No | Freeze processing while dispute is resolved |
| Right to object | Art. 21 | Opt-out of sale/sharing | Especially for direct marketing and LI-based processing |
| No automated decision-making | Art. 22 | No | Human review option for decisions with legal/significant effects |

### Cross-border transfer mechanisms

| Mechanism | Use when |
|---|---|
| Adequacy decision | Transferring to a country the EU Commission has approved (e.g., UK post-IDTA, Japan, Canada) |
| Standard Contractual Clauses (SCCs) | Most common for transfers to non-adequate countries (e.g., US). Use 2021 SCCs. |
| Binding Corporate Rules (BCRs) | Intra-group transfers within a large multinational; requires DPA approval, lengthy process |
| Derogations (Art. 49) | Narrow exceptions: explicit consent, performance of contract, vital interests. Not for systematic transfers. |

---

## Common tasks

### 1. Implement a GDPR compliance checklist

Use this as a product/engineering launch gate:

**Data inventory**
- [ ] Record of Processing Activities (RoPA) created and up to date
- [ ] Lawful basis documented for each processing activity
- [ ] Retention periods defined for each data category
- [ ] Third-party processors identified; DPAs signed with each

**Technical controls**
- [ ] Personal data encrypted at rest and in transit
- [ ] Access to personal data is role-based and audited
- [ ] Pseudonymization applied where full identification is not needed
- [ ] Automated deletion jobs scheduled per retention policy

**User-facing obligations**
- [ ] Privacy policy published, accessible, and up to date
- [ ] Cookie consent mechanism in place (see task 2)
- [ ] Data subject request workflow implemented (see task 4)
- [ ] Age verification where required (special categories, children's data)

**Organizational**
- [ ] DPO appointed (if required) and contact details published
- [ ] Data breach response procedure documented and tested
- [ ] DPIA completed for high-risk processing activities (see task 3)
- [ ] Staff privacy training completed

---

### 2. Design consent management (cookie banners and preference center)

**The consent bar is higher than most implementations meet.** For GDPR, pre-ticked
boxes, bundled consent, and making "reject" harder than "accept" are all invalid.

**Cookie categories to surface to users:**

| Category | Examples | Requires consent? |
|---|---|---|
| Strictly necessary | Session auth, load balancing, CSRF tokens | No - but must disclose |
| Functional / preferences | Language, theme, remembered settings | Yes (GDPR), disclose (CCPA) |
| Analytics / performance | Google Analytics, Heap, session recording | Yes (GDPR), opt-out (CCPA) |

From mkurman/zorai, MIT.

More from mkurman/zorai

Signals

Stars
325
Forks
24
Open issues
0
Last commit (this folder)
May 5, 2026 (5 months ago)
Last release
Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Website
zorai.app/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from mkurman

Cite this page

privacy-compliance skill. Agent Mart. https://agentmart.dev/skills/mkurman-privacy-compliance (last updated 2026-10-24)