Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Maps how personal data flows through a system and produces GDPR artifacts — a Record of Processing Activities (RoPA), lawful-basis analysis, retention schedule, and data-subject-rights readiness — for each processing activity. Use this skill when the user asks to "map our data", "create a RoPA / Article 30 record", "do a GDPR data mapping", "figure out our lawful basis", "build a retention schedule", "prepare for a DSAR / data subject request", or assess privacy/personal-data handling. Not legal
.claude/skills/jayrha-gdpr-data-mapper/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 22% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 31% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 37% | 0% |
Produce a clear, auditable map of personal-data processing and the core GDPR artifacts that depend on it. Output is a structured draft to be reviewed by a DPO or counsel — this skill does not give legal advice.
Keywords: GDPR, data mapping, RoPA, Article 30, record of processing, lawful basis, consent, legitimate interest, retention schedule, data subject rights, DSAR, data minimization, special category data, processor, controller, cross-border transfer, DPIA.
templates/ropa-template.md): controller/processor role, purpose, data categories, data subjects, recipients, retention, transfers, and security measures.references/lawful-basis-guide.md. Exactly one of the six bases per purpose; document the reasoning. For legitimate interest, note that a balancing test (LIA) is required.references/retention-and-rights.md). "Indefinite" is not acceptable.| Question | Where | | --- | --- | | Which lawful basis applies? | references/lawful-basis-guide.md | | How long can we keep this? | references/retention-and-rights.md | | What goes in the record? | templates/ropa-template.md | | Does this need a DPIA? | Large-scale + (special category OR systematic monitoring OR new tech) → likely yes |
| Field | Value | | --- | --- | | Activity | Marketing newsletter | | Role | Controller | | Purpose | Send product updates to subscribers | | Data categories | Name, email, open/click events | | Data subjects | Newsletter subscribers | | Lawful basis | Consent (Art. 6(1)(a)) — opt-in checkbox, logged | | Recipients | Email service provider (processor, DPA signed) | | Retention | Until unsubscribe + 30 days, then deleted | | Transfers | ESP in US — SCCs in place | | Rights | Unsubscribe link (objection); export on request (portability) |
> This is a drafting aid, not legal advice. Have a DPO or qualified counsel review the output.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 25,492 | 32,770 | +29% | 1 | 1 | 0% | 4,540 | 7,231 | +59% | 0 | 0 | — |
case-02 | fail→fail | 28,780 | 34,385 | +19% | 1 | 1 | 0% | 5,348 | 7,228 | +35% | 0 | 0 | — |
case-03 | fail→fail | 31,852 | 33,784 | +6% | 1 | 1 | 0% | 6,237 | 6,800 | +9% | 0 | 0 | — |
case-04 | pass→pass | 13,524 | 12,267 | -9% | 1 | 1 | 0% | 2,578 | 3,155 | +22% | 0 | 0 | — |
case-05 | pass→pass | 13,404 | 12,554 | -6% | 1 | 1 | 0% | 2,446 | 3,202 | +31% | 0 | 0 | — |
case-06 | pass→pass | 13,172 | 12,316 | -6% | 1 | 1 | 0% | 2,258 | 3,101 | +37% | 0 | 0 | — |
case-07 | pass→pass | 14,347 | 13,263 | -8% | 1 | 1 | 0% | 2,522 | 3,303 | +31% | 0 | 0 | — |
case-08 | pass→pass | 9,638 | 11,636 | +21% | 1 | 1 | 0% | 1,953 | 3,078 | +58% | 0 | 0 | — |
case-09 | pass→pass | 13,868 | 10,498 | -24% | 1 | 1 | 0% | 2,396 | 2,838 | +18% | 0 | 0 | — |
case-10 | pass→pass | 16,875 | 19,738 | +17% | 1 | 1 | 0% | 2,878 | 4,165 | +45% | 0 | 0 | — |
case-11 | pass→pass | 15,436 | 15,855 | +3% | 1 | 1 | 0% | 2,661 | 3,646 | +37% | 0 | 0 | — |
case-12 | pass→pass | 16,618 | 19,625 | +18% | 1 | 1 | 0% | 2,793 | 4,198 | +50% | 0 | 0 | — |
case-13 | pass→pass | 15,466 | 14,465 | -6% | 1 | 1 | 0% | 2,626 | 3,416 | +30% | 0 | 0 | — |
case-14 | fail→pass | 11,421 | 9,041 | -21% | 1 | 1 | 0% | 2,178 | 2,614 | +20% | 0 | 0 | — |
case-15 | pass→pass | 12,582 | 12,082 | -4% | 1 | 1 | 0% | 2,287 | 2,880 | +26% | 0 | 0 | — |
case-16 | fail→pass | 15,554 | 14,387 | -8% | 1 | 1 | 0% | 2,896 | 3,553 | +23% | 0 | 0 | — |
case-17 | pass→pass | 19,553 | 15,152 | -23% | 1 | 1 | 0% | 2,787 | 3,661 | +31% | 0 | 0 | — |
case-18 | pass→pass | 11,276 | 9,673 | -14% | 1 | 1 | 0% | 1,643 | 2,681 | +63% | 0 | 0 | — |
case-19 | pass→pass | 16,137 | 18,176 | +13% | 1 | 1 | 0% | 3,011 | 4,017 | +33% | 0 | 0 | — |
case-20 | pass→pass | 12,729 | 14,636 | +15% | 1 | 1 | 0% | 2,276 | 3,420 | +50% | 0 | 0 | — |
case-21 | fail→fail | 24,408 | 18,523 | -24% | 1 | 1 | 0% | 5,206 | 4,568 | -12% | 0 | 0 | — |
case-22 | fail→fail | 15,540 | 16,958 | +9% | 1 | 1 | 0% | 2,906 | 4,097 | +41% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +16% |
Other measured skills in the registry, with their headline benchmark lift.