Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when reviewing, designing, or modifying Java enterprise systems that may support EU Digital Markets Act gatekeeper-platform concerns, core platform services, interoperability, business-user data access, consent-dependent data combination, ranking, self-preferencing, advertising transparency, or anti-circumvention controls. This should trigger for requests such as Review a Java platform for DMA controls; Design interoperability and business-user data access evidence; Add ranking, consent, pre
.claude/skills/jabrena-808-regulations-eu-digital-markets-act/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 195% | 0% |
Use this Skill to review Java enterprise applications, platform APIs, marketplaces, app stores, advertising systems, ranking systems, identity services, browser or operating-system integrations, messaging interoperability, business-user portals, data access APIs, analytics pipelines, CI/CD workflows, or operational tooling that may support Digital Markets Act (DMA) gatekeeper-platform obligations.
Apply this Skill to determine what engineering controls, compliance evidence, and escalation paths are needed before a system is released, connected to production platform data, exposed to business users, or used to operate a core platform service.
This Skill is not legal advice. It helps Java engineers, architects, tech leads, platform teams, product teams, and reviewers identify when DMA concerns may apply and how to translate gatekeeper-platform expectations into enterprise architecture controls such as interoperability interfaces, business-user data access APIs, consent and preference evidence, ranking and self-preferencing audit signals, advertising transparency evidence, app-store or marketplace access controls, anti-circumvention guardrails, observability, change control, documentation, and compliance evidence handoff.
The purpose of this Skill is to increase awareness of potential gaps in the system and create engineering evidence for qualified review. The response produced by this Skill does not represent legal advice, a legal opinion, a gatekeeper designation, a core platform service classification, or a final regulatory determination.
The main question is:
> When does a Java enterprise platform require DMA-aware gatekeeper controls, and what should developers build differently?
External reference: Digital Markets Act Regulation (EU) 2022/1925.
Digital Markets Act chapters summary reference: DMA chapters summary.
Java engineering examples reference: DMA engineering examples.
Report template asset: DMA engineering review report template.
This Skill applies to:
Treat gatekeeper designation, core platform service scope, obligation applicability, consent interpretation, self-preferencing assessments, fair and reasonable access terms, suspension or exemption requests, and regulatory interpretation as governance decisions for legal, compliance, platform governance, product, privacy, security, risk, competition, and executive accountability owners.
Engineering teams should still create evidence that makes those decisions reviewable:
Translate Digital Markets Act concerns into engineering controls for Java enterprise systems. Do not provide legal advice or replace review by legal, compliance, platform governance, product, privacy, security, risk, competition, or executive accountability owners.
Read references/808-regulations-eu-digital-markets-act-chapters-summary.md, references/808-regulations-eu-digital-markets-act-engineering-examples.md, and assets/reports/808-eu-digital-markets-act-engineering-review-report-template.md in that order. Use the chapters summary for DMA chapter, article, scope, designation, obligations, interoperability, anti-circumvention, monitoring, enforcement, reporting, and owner-handoff context. Use the engineering examples for Java control patterns such as interoperability interfaces, business-user data access, consent and preference evidence, ranking audit signals, export workflows, anti-circumvention release gates, observability, and compliance evidence handoff. Do not start implementation review until the DMA chapters summary, examples reference, and report template are understood.
Identify service context, possible core platform service signals, gatekeeper-scope signals, business-user and end-user journeys, platform owners, data owners, product owners, privacy owners, security owners, compliance owners, deployment environments, APIs, data stores, event streams, ranking systems, advertising systems, consent flows, access policies, interoperability interfaces, export workflows, and production release paths. Escalate gatekeeper designation, core platform service classification, obligation applicability, consent interpretation, self-preferencing assessment, fair access terms, suspension or exemption questions, and regulatory interpretation to qualified owners.
Review Java code, configuration, APIs, DTOs, repositories, schemas, migrations, Kafka messages, ranking code, feature flags, experiments, consent and preference records, audit logs, metrics, traces, dashboards, alerts, export jobs, business-user portals, documentation, tests, release records, and compliance reports. Check for gaps between claimed controls and reviewable evidence.
Map DMA concerns to engineering actions: interoperability API contracts, reference-offer evidence, data access APIs, export workflows, consent and preference records, ranking and self-preferencing audit signals, advertising transparency metrics, business-user access terms, anti-circumvention guardrails, least privilege, observability, documentation, change approval, and compliance evidence handoff.
Use assets/reports/808-eu-digital-markets-act-engineering-review-report-template.md to produce a concise engineering review with scope, evidence reviewed, DMA risk signals, potential violation or non-compliance signals, engineering gaps, recommended controls, owner handoffs, residual risks, release decision, and validation steps. State explicitly that gatekeeper designation, core platform service scope, obligation applicability, consent interpretation, self-preferencing assessments, fair access terms, and regulatory interpretation require qualified owner review.
For detailed guidance, examples, and constraints, see:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 36,834 | 9,578 | -74% | 1 | 1 | 0% | 3,676 | 3,855 | +5% | 0 | 0 | — |
case-01 | fail→fail | 36,994 | 21,328 | -42% | 1 | 1 | 0% | 6,220 | 5,940 | -5% | 0 | 0 | — |
case-02 | pass→pass | 33,700 | 32,302 | -4% | 1 | 1 | 0% | 6,219 | 7,523 | +21% | 0 | 0 | — |
case-03 | fail→pass | 36,842 | 26,403 | -28% | 1 | 1 | 0% | 6,212 | 6,491 | +4% | 0 | 0 | — |
case-04 | pass→fail | 23,920 | 50,044 | +109% | 1 | 1 | 0% | 3,765 | 7,319 | +94% | 0 | 0 | — |
case-05 | pass→fail | 24,506 | 21,775 | -11% | 1 | 1 | 0% | 3,830 | 5,727 | +50% | 0 | 0 | — |
case-07 | pass→pass | 17,053 | 20,222 | +19% | 1 | 1 | 0% | 2,529 | 5,665 | +124% | 0 | 0 | — |
case-08 | pass→pass | 22,087 | 25,134 | +14% | 1 | 1 | 0% | 2,685 | 6,573 | +145% | 0 | 0 | — |
case-09 | fail→pass | 17,037 | 17,349 | +2% | 1 | 1 | 0% | 2,619 | 5,096 | +95% | 0 | 0 | — |
case-10 | fail→pass | 19,416 | 20,729 | +7% | 1 | 1 | 0% | 2,873 | 5,684 | +98% | 0 | 0 | — |
case-11 | fail→pass | 21,360 | 21,850 | +2% | 1 | 1 | 0% | 3,249 | 6,341 | +95% | 0 | 0 | — |
case-12 | pass→pass | 15,799 | 17,518 | +11% | 1 | 1 | 0% | 2,381 | 5,341 | +124% | 0 | 0 | — |
case-13 | pass→pass | 22,786 | 24,880 | +9% | 1 | 1 | 0% | 3,660 | 6,594 | +80% | 0 | 0 | — |
case-14 | fail→pass | 12,490 | 17,187 | +38% | 1 | 1 | 0% | 1,774 | 5,238 | +195% | 0 | 0 | — |
case-15 | fail→pass | 20,827 | 23,635 | +13% | 1 | 1 | 0% | 3,128 | 6,199 | +98% | 0 | 0 | — |
case-16 | pass→pass | 18,321 | 25,647 | +40% | 1 | 1 | 0% | 3,221 | 6,607 | +105% | 0 | 0 | — |
case-17 | pass→pass | 17,868 | 21,057 | +18% | 1 | 1 | 0% | 2,729 | 5,799 | +112% | 0 | 0 | — |
case-18 | pass→pass | 19,716 | 19,707 | -0% | 1 | 1 | 0% | 2,976 | 5,385 | +81% | 0 | 0 | — |
case-19 | pass→pass | 12,850 | 12,289 | -4% | 1 | 1 | 0% | 1,945 | 4,039 | +108% | 0 | 0 | — |
case-20 | fail→pass | 24,330 | 29,356 | +21% | 1 | 1 | 0% | 4,009 | 7,110 | +77% | 0 | 0 | — |
case-21 | fail→pass | 13,612 | 19,870 | +46% | 1 | 1 | 0% | 1,982 | 5,524 | +179% | 0 | 0 | — |
case-22 | pass→pass | 20,120 | 17,785 | -12% | 1 | 1 | 0% | 3,027 | 5,096 | +68% | 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 +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.