Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Senior Regulatory Affairs Manager expertise for HealthTech and MedTech companies. Provides strategic regulatory guidance, submission management, regulatory pathway analysis, global compliance coordination, and cross-functional team leadership. Use for regulatory strategy development, submission planning, regulatory risk assessment, and team coordination activities.
.claude/skills/davila7-regulatory-affairs-head/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | — | 2 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-21 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 79% | 0% |
Expert-level regulatory affairs leadership for HealthTech and MedTech companies with deep knowledge of global regulatory frameworks, submission strategies, and cross-functional team coordination.
Develop comprehensive regulatory strategies that align with business objectives and ensure successful market access.
Key Activities:
Lead all aspects of regulatory submissions from pre-submission through post-market surveillance.
Submission Workflow:
Coordinate regulatory activities across all departments ensuring alignment and compliance.
Team Coordination Protocol:
Identify, assess, and mitigate regulatory risks throughout the product lifecycle.
Risk Assessment Framework:
1. REGULATORY IMPACT ASSESSMENT
├── Market access implications
├── Timeline and resource impact
├── Competitive positioning effects
└── Post-market obligations
2. MITIGATION STRATEGY DEVELOPMENT
├── Preventive controls implementation
├── Contingency planning
├── Communication protocols
└── Monitoring and review processesApply this framework for all strategic regulatory decisions:
Step 1: Regulatory Impact Assessment
Step 2: Stakeholder Alignment
Step 3: Implementation Planning
Step 4: Monitoring and Review
Monitor these regulatory performance metrics:
For Regulatory Updates: Use standardized templates in assets/communication-templates/ For Regulatory Submissions: Follow checklists in references/submission-checklists/ For Team Training: Utilize materials in assets/training-materials/ For Escalations: Follow protocols in references/escalation-procedures.md
regulatory_tracker.py: Automated submission status monitoringcompliance_checker.py: Regulatory compliance verification toolsubmission_timeline.py: Project timeline management and reportingeu-mdr-submission-guide.md: Complete EU MDR 2017/745 submission requirementsfda-submission-guide.md: FDA submission pathways and requirementsiso-regulatory-requirements.md: ISO 13485 and related standardsglobal-regulatory-pathways.md: International regulatory requirementsescalation-procedures.md: Internal and external escalation protocolscommunication-templates/: Standardized regulatory communication templatessubmission-checklists/: Comprehensive submission preparation checkliststraining-materials/: Regulatory training presentations and materialsregulatory-forms/: Standard regulatory forms and templates| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | fail→pass | 7,740 | 3,727 | -52% | 1 | 1 | 0% | 1,529 | 1,642 | +7% | 0 | 0 | — |
case-22 | fail→pass | 7,094 | 4,141 | -42% | 1 | 1 | 0% | 1,191 | 1,834 | +54% | 0 | 0 | — |
case-01 | fail→fail | 44,231 | 29,635 | -33% | 1 | 1 | 0% | 5,121 | 6,154 | +20% | 0 | 0 | — |
case-02 | fail→fail | 29,353 | 28,849 | -2% | 1 | 1 | 0% | 4,822 | 6,506 | +35% | 0 | 0 | — |
case-03 | fail→fail | 22,722 | 23,771 | +5% | 1 | 1 | 0% | 3,874 | 4,960 | +28% | 0 | 0 | — |
case-04 | pass→pass | 17,872 | 18,665 | +4% | 1 | 1 | 0% | 3,887 | 4,534 | +17% | 0 | 0 | — |
case-05 | pass→pass | 21,043 | 28,855 | +37% | 1 | 1 | 0% | 3,920 | 6,123 | +56% | 0 | 0 | — |
case-06 | pass→pass | 17,066 | 14,210 | -17% | 1 | 1 | 0% | 3,035 | 3,287 | +8% | 0 | 0 | — |
case-07 | fail→pass | 5,671 | 3,224 | -43% | 1 | 1 | 0% | 953 | 1,507 | +58% | 0 | 0 | — |
case-08 | fail→pass | 6,549 | 4,607 | -30% | 1 | 1 | 0% | 1,209 | 1,714 | +42% | 0 | 0 | — |
case-09 | fail→pass | 4,402 | 2,118 | -52% | 1 | 1 | 0% | 752 | 1,346 | +79% | 0 | 0 | — |
case-10 | fail→pass | 11,600 | 4,254 | -63% | 1 | 1 | 0% | 2,055 | 1,648 | -20% | 0 | 0 | — |
case-11 | fail→pass | 7,841 | 1,564 | -80% | 1 | 1 | 0% | 1,478 | 1,220 | -17% | 0 | 0 | — |
case-12 | fail→pass | 4,588 | 2,775 | -40% | 1 | 1 | 0% | 787 | 1,392 | +77% | 0 | 0 | — |
case-13 | fail→pass | 8,897 | 2,520 | -72% | 1 | 1 | 0% | 1,519 | 1,248 | -18% | 0 | 0 | — |
case-14 | fail→pass | 7,428 | 1,710 | -77% | 1 | 1 | 0% | 1,334 | 1,250 | -6% | 0 | 0 | — |
case-15 | fail→pass | 8,408 | 1,378 | -84% | 1 | 1 | 0% | 888 | 1,140 | +28% | 0 | 0 | — |
case-16 | fail→pass | 5,556 | 2,807 | -49% | 1 | 1 | 0% | 832 | 1,414 | +70% | 0 | 0 | — |
case-17 | fail→pass | 3,536 | 4,403 | +25% | 1 | 1 | 0% | 580 | 1,249 | +115% | 0 | 0 | — |
case-18 | fail→pass | 3,434 | 2,161 | -37% | 1 | 1 | 0% | 482 | 1,331 | +176% | 0 | 0 | — |
case-19 | fail→pass | 10,244 | 6,372 | -38% | 1 | 1 | 0% | 1,774 | 2,086 | +18% | 0 | 0 | — |
case-20 | fail→pass | 10,571 | 6,889 | -35% | 1 | 1 | 0% | 1,723 | 2,108 | +22% | 0 | 0 | — |
case-23 | fail→pass | 12,133 | 5,002 | -59% | 1 | 1 | 0% | 2,022 | 1,823 | -10% | 0 | 0 | — |
case-24 | pass→pass | 12,319 | 14,745 | +20% | 1 | 1 | 0% | 2,275 | 3,491 | +53% | 0 | 0 | — |
case-25 | pass→pass | 9,201 | 3,096 | -66% | 1 | 1 | 0% | 1,485 | 1,613 | +9% | 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. 25 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 25 comparable cases.
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.