Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generates structured privacy and data protection law briefings across US, EU, UK, and other jurisdictions. Organizes by jurisdiction with compliance deadlines, enforcement actions, and legislative changes. Use when preparing privacy law briefings, compliance updates, regulatory change summaries, or data protection landscape reviews.
.claude/skills/thomasmoreai-privacy-law-updates/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 77% | 0% |
Produces a structured briefing on recent privacy and data protection developments, oriented toward compliance planning and executive decision-making.
Confirm before generating:
| Element | Content | |---|---| | Critical deadlines | Compliance dates requiring immediate action | | Major enforcement | Fines/orders signaling regulatory priorities | | New obligations | Requirements not previously in effect | | Strategic flags | Developments affecting product roadmap or vendors |
For each jurisdiction, use this entry template:
### [Jurisdiction]
#### [Development Title]
- **Type**: Legislation | Guidance | Enforcement | Court Decision
- **Effective date**: [date or timeline]
- **Scope**: [entities, data types, activities covered]
- **Key requirements/holdings**: [bullet list]
- **Delta from prior law**: [what changed]
- **Operational impact**: [systems, processes, documentation affected]
- **Penalties**: [non-compliance consequences]
- **Exemptions/safe harbors**: [if any]Cover only topics with material developments:
| Topic | Capture | |---|---| | Cross-border transfers | New mechanisms, adequacy decisions, SCCs updates | | Consent & notice | Changed standards, dark-pattern enforcement | | Data subject rights | Access, deletion, portability changes | | Breach notification | Amended timelines, reporting thresholds | | AI governance | Automated decision-making rules, transparency mandates | | Children's privacy | Age verification, parental consent, design codes | | Biometric data | New state/national laws, consent requirements |
[VERIFY]| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,602 | 35,742 | +29% | 1 | 1 | 0% | 4,698 | 6,714 | +43% | 0 | 0 | — |
case-07 | fail→pass | 17,197 | 24,242 | +41% | 1 | 1 | 0% | 3,063 | 4,343 | +42% | 0 | 0 | — |
case-02 | fail→fail | 34,928 | 34,373 | -2% | 1 | 1 | 0% | 6,230 | 6,555 | +5% | 0 | 0 | — |
case-03 | fail→fail | 37,000 | 32,839 | -11% | 1 | 1 | 0% | 6,220 | 6,871 | +10% | 0 | 0 | — |
case-04 | fail→fail | 18,716 | 21,911 | +17% | 1 | 1 | 0% | 2,994 | 4,622 | +54% | 0 | 0 | — |
case-05 | fail→pass | 17,601 | 16,038 | -9% | 1 | 1 | 0% | 3,052 | 3,695 | +21% | 0 | 0 | — |
case-06 | fail→pass | 17,685 | 14,663 | -17% | 1 | 1 | 0% | 3,348 | 3,242 | -3% | 0 | 0 | — |
case-08 | pass→pass | 11,596 | 15,279 | +32% | 1 | 1 | 0% | 1,899 | 3,109 | +64% | 0 | 0 | — |
case-09 | pass→pass | 25,733 | 30,771 | +20% | 1 | 1 | 0% | 3,942 | 5,379 | +36% | 0 | 0 | — |
case-10 | pass→pass | 25,874 | 24,189 | -7% | 1 | 1 | 0% | 4,511 | 4,614 | +2% | 0 | 0 | — |
case-11 | pass→fail | 15,209 | 26,118 | +72% | 1 | 1 | 0% | 2,796 | 5,034 | +80% | 0 | 0 | — |
case-12 | pass→pass | 17,179 | 14,381 | -16% | 1 | 1 | 0% | 2,887 | 3,096 | +7% | 0 | 0 | — |
case-13 | fail→pass | 21,752 | 22,947 | +5% | 1 | 1 | 0% | 2,592 | 3,631 | +40% | 0 | 0 | — |
case-14 | pass→pass | 11,031 | 20,699 | +88% | 1 | 1 | 0% | 2,057 | 4,362 | +112% | 0 | 0 | — |
case-15 | fail→pass | 17,464 | 25,025 | +43% | 1 | 1 | 0% | 2,871 | 5,070 | +77% | 0 | 0 | — |
case-16 | pass→pass | 14,072 | 21,452 | +52% | 1 | 1 | 0% | 2,608 | 4,640 | +78% | 0 | 0 | — |
case-17 | pass→pass | 14,541 | 27,077 | +86% | 1 | 1 | 0% | 2,816 | 5,741 | +104% | 0 | 0 | — |
case-18 | fail→fail | 14,650 | 12,536 | -14% | 1 | 1 | 0% | 2,319 | 2,707 | +17% | 0 | 0 | — |
case-19 | pass→pass | 18,195 | 19,806 | +9% | 1 | 1 | 0% | 3,728 | 4,457 | +20% | 0 | 0 | — |
case-20 | pass→pass | 12,399 | 16,443 | +33% | 1 | 1 | 0% | 2,191 | 3,606 | +65% | 0 | 0 | — |
case-21 | pass→pass | 16,369 | 14,276 | -13% | 1 | 1 | 0% | 2,890 | 3,343 | +16% | 0 | 0 | — |
case-22 | pass→pass | 12,747 | 12,205 | -4% | 1 | 1 | 0% | 2,324 | 2,832 | +22% | 0 | 0 | — |
case-23 | pass→pass | 19,424 | 22,178 | +14% | 1 | 1 | 0% | 3,339 | 3,426 | +3% | 0 | 0 | — |
case-24 | pass→pass | 10,595 | 13,842 | +31% | 1 | 1 | 0% | 2,058 | 2,756 | +34% | 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. 24 cases were attempted. The headline lift of +17 percentage points is the difference between those two pass rates over the 24 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.
Other measured skills in the registry, with their headline benchmark lift.