Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Quality & Regulatory agent for ISO 13485 QMS, MDR compliance, FDA submissions, GDPR/DSGVO, and ISMS audits. Orchestrates ra-qm-team skills. Spawn when users need regulatory strategy, audit preparation, CAPA management, risk management, or compliance documentation.
.claude/skills/alirezarezvani-cs-quality-regulatory/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-10 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-09 | ✓→✓ | ＝ Same ✓ | 52% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 87% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 97% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 110% | 0% |
Regulatory affairs and quality management specialist for medical device and healthcare companies. Covers ISO 13485, EU MDR 2017/745, FDA (510(k)/PMA), GDPR/DSGVO, and ISO 27001 ISMS.
ra-qm-team/quality-manager-qms-iso13485 — QMS implementation, process managementra-qm-team/quality-manager-qmr — Management review, quality metricsra-qm-team/quality-documentation-manager — Document control, SOP managementra-qm-team/qms-audit-expert — Internal/external audit preparationra-qm-team/capa-officer — Root cause analysis, corrective actionsra-qm-team/regulatory-affairs-head — Regulatory strategy, submission planningra-qm-team/mdr-745-specialist — EU MDR classification, technical documentationra-qm-team/fda-consultant-specialist — 510(k)/PMA/De Novo pathway guidancera-qm-team/risk-management-specialist — ISO 14971 risk managementra-qm-team/information-security-manager-iso27001 — ISMS design, security controlsra-qm-team/isms-audit-expert — ISO 27001 audit preparationra-qm-team/gdpr-dsgvo-expert — Privacy impact assessments, data subject rightsqms-audit-expert or isms-audit-expertquality-documentation-managercapa-officermdr-745-specialist (Annex VIII rules)capa-officergdpr-dsgvo-expert| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→pass | 14,136 | 12,787 | -10% | 1 | 1 | 0% | 2,220 | 3,365 | +52% | 0 | 0 | — |
case-01 | pass→pass | 6,897 | 8,264 | +20% | 1 | 1 | 0% | 1,401 | 2,619 | +87% | 0 | 0 | — |
case-02 | pass→pass | 5,778 | 6,746 | +17% | 1 | 1 | 0% | 1,103 | 2,178 | +97% | 0 | 0 | — |
case-03 | pass→pass | 4,281 | 3,636 | -15% | 1 | 1 | 0% | 768 | 1,611 | +110% | 0 | 0 | — |
case-04 | pass→pass | 17,735 | 22,636 | +28% | 1 | 1 | 0% | 3,295 | 4,195 | +27% | 0 | 0 | — |
case-05 | pass→pass | 6,204 | 7,342 | +18% | 1 | 1 | 0% | 1,145 | 2,319 | +103% | 0 | 0 | — |
case-06 | pass→pass | 10,463 | 11,420 | +9% | 1 | 1 | 0% | 2,027 | 3,118 | +54% | 0 | 0 | — |
case-07 | pass→pass | 13,928 | 9,249 | -34% | 1 | 1 | 0% | 1,431 | 2,603 | +82% | 0 | 0 | — |
case-08 | pass→pass | 4,529 | 5,072 | +12% | 1 | 1 | 0% | 675 | 1,752 | +160% | 0 | 0 | — |
case-10 | fail→pass | 10,242 | 9,538 | -7% | 1 | 1 | 0% | 1,876 | 2,598 | +38% | 0 | 0 | — |
case-11 | pass→pass | 3,781 | 6,318 | +67% | 1 | 1 | 0% | 678 | 2,090 | +208% | 0 | 0 | — |
case-12 | pass→pass | 5,153 | 7,753 | +50% | 1 | 1 | 0% | 913 | 2,441 | +167% | 0 | 0 | — |
case-13 | pass→pass | 4,564 | 5,528 | +21% | 1 | 1 | 0% | 889 | 2,020 | +127% | 0 | 0 | — |
case-14 | pass→pass | 3,685 | 2,948 | -20% | 1 | 1 | 0% | 717 | 1,443 | +101% | 0 | 0 | — |
case-15 | pass→pass | 11,161 | 2,697 | -76% | 1 | 1 | 0% | 1,915 | 1,435 | -25% | 0 | 0 | — |
case-16 | pass→pass | 12,455 | 18,407 | +48% | 1 | 1 | 0% | 2,370 | 2,528 | +7% | 0 | 0 | — |
case-17 | pass→pass | 9,933 | 7,260 | -27% | 1 | 1 | 0% | 1,457 | 2,187 | +50% | 0 | 0 | — |
case-18 | pass→pass | 7,628 | 6,857 | -10% | 1 | 1 | 0% | 1,189 | 2,466 | +107% | 0 | 0 | — |
case-19 | pass→pass | 3,765 | 5,903 | +57% | 1 | 1 | 0% | 545 | 2,090 | +283% | 0 | 0 | — |
case-20 | fail→fail | 18,781 | 20,688 | +10% | 1 | 1 | 0% | 3,900 | 5,542 | +42% | 0 | 0 | — |
case-21 | fail→fail | 14,252 | 16,938 | +19% | 1 | 1 | 0% | 2,782 | 4,212 | +51% | 0 | 0 | — |
case-22 | fail→fail | 21,735 | 21,743 | +0% | 1 | 1 | 0% | 3,300 | 4,030 | +22% | 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 +5 percentage points is the difference between those two pass rates over the 22 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.