Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Router/index for the 15 regulatory & quality-management skills bundled in this plugin (ISO 13485 QMS, EU MDR 2017/745, FDA submissions under QMSR, ISO 14971 risk, CAPA, document control, ISO 27001/ISMS, ISO 42001 AIMS, EU AI Act, GDPR/DSGVO, SOC 2, auditing). Use when a compliance request doesn't obviously match one skill and you need to pick the right one (e.g., 'prepare us for an ISO 13485 audit', 'is my AI system high-risk under the AI Act').
.claude/skills/alirezarezvani-ra-qm-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-23 | ✗→✓ | ▲ Improved | 88% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -18% | 0% |
This plugin bundles 15 compliance skills for HealthTech/MedTech organizations (this router is the 16th folder under ra-qm-team/skills/). Each skill is self-contained.
Match the request, then load ra-qm-team/skills/<skill>/SKILL.md. If multiple rows match, ask one clarifying question first.
| Request signals | Skill | Path | |---|---|---| | Regulatory strategy, pathway selection, submissions planning | regulatory-affairs-head | skills/regulatory-affairs-head/ | | Management review, quality KPIs, QMR governance | quality-manager-qmr | skills/quality-manager-qmr/ | | ISO 13485 QMS implementation, process control | quality-manager-qms-iso13485 | skills/quality-manager-qms-iso13485/ | | ISO 14971 risk analysis, FMEA, risk files | risk-management-specialist | skills/risk-management-specialist/ | | Root cause analysis, corrective/preventive actions | capa-officer | skills/capa-officer/ | | Document control, 21 CFR Part 11, DHF/DMR/DHR | quality-documentation-manager | skills/quality-documentation-manager/ | | ISO 13485 internal audits, NC classification | qms-audit-expert | skills/qms-audit-expert/ | | ISO 27001 audit planning and execution | isms-audit-expert | skills/isms-audit-expert/ | | ISMS design, security risk assessment | information-security-manager-iso27001 | skills/information-security-manager-iso27001/ | | EU MDR classification, technical files, PSUR | mdr-745-specialist | skills/mdr-745-specialist/ | | FDA 510(k)/PMA/De Novo, QMSR | fda-consultant-specialist | skills/fda-consultant-specialist/ | | GDPR/DSGVO, DPIA, data subject rights | gdpr-dsgvo-expert | skills/gdpr-dsgvo-expert/ | | EU AI Act risk classification, obligations | eu-ai-act-specialist | skills/eu-ai-act-specialist/ | | ISO/IEC 42001 AI management system | iso42001-specialist | skills/iso42001-specialist/ | | SOC 2 Type I/II readiness, trust criteria | soc2-compliance | skills/soc2-compliance/ |
bash# Example: route a risk-analysis request cat ra-qm-team/skills/risk-management-specialist/SKILL.md python3 ra-qm-team/skills/risk-management-specialist/scripts/risk_matrix_calculator.py --help
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | fail→pass | 6,791 | 6,061 | -11% | 1 | 1 | 0% | 1,085 | 2,040 | +88% | 0 | 0 | — |
case-01 | fail→fail | 17,992 | 15,359 | -15% | 1 | 1 | 0% | 3,131 | 3,679 | +18% | 0 | 0 | — |
case-02 | fail→fail | 23,224 | 20,422 | -12% | 1 | 1 | 0% | 4,275 | 4,791 | +12% | 0 | 0 | — |
case-03 | pass→fail | 22,005 | 20,986 | -5% | 1 | 1 | 0% | 4,147 | 4,911 | +18% | 0 | 0 | — |
case-04 | fail→pass | 6,628 | 4,108 | -38% | 1 | 1 | 0% | 1,085 | 1,614 | +49% | 0 | 0 | — |
case-05 | pass→pass | 13,443 | 8,113 | -40% | 1 | 1 | 0% | 2,275 | 2,235 | -2% | 0 | 0 | — |
case-06 | pass→pass | 16,003 | 10,837 | -32% | 1 | 1 | 0% | 2,931 | 2,787 | -5% | 0 | 0 | — |
case-07 | fail→pass | 12,765 | 11,138 | -13% | 1 | 1 | 0% | 2,202 | 2,353 | +7% | 0 | 0 | — |
case-08 | fail→pass | 17,355 | 10,148 | -42% | 1 | 1 | 0% | 2,931 | 2,713 | -7% | 0 | 0 | — |
case-09 | fail→pass | 13,642 | 7,135 | -48% | 1 | 1 | 0% | 2,502 | 2,058 | -18% | 0 | 0 | — |
case-10 | pass→pass | 11,834 | 8,867 | -25% | 1 | 1 | 0% | 2,152 | 1,826 | -15% | 0 | 0 | — |
case-11 | pass→pass | 15,991 | 10,501 | -34% | 1 | 1 | 0% | 2,960 | 2,690 | -9% | 0 | 0 | — |
case-12 | fail→pass | 11,899 | 9,186 | -23% | 1 | 1 | 0% | 2,266 | 2,545 | +12% | 0 | 0 | — |
case-13 | pass→pass | 11,742 | 6,795 | -42% | 1 | 1 | 0% | 2,091 | 1,948 | -7% | 0 | 0 | — |
case-14 | pass→pass | 10,058 | 7,530 | -25% | 1 | 1 | 0% | 1,718 | 2,185 | +27% | 0 | 0 | — |
case-15 | pass→pass | 8,494 | 5,808 | -32% | 1 | 1 | 0% | 1,573 | 1,865 | +19% | 0 | 0 | — |
case-16 | pass→pass | 6,958 | 4,695 | -33% | 1 | 1 | 0% | 1,268 | 1,731 | +37% | 0 | 0 | — |
case-17 | fail→pass | 17,353 | 2,829 | -84% | 1 | 1 | 0% | 3,405 | 1,322 | -61% | 0 | 0 | — |
case-18 | fail→pass | 15,149 | 2,224 | -85% | 1 | 1 | 0% | 2,609 | 1,214 | -53% | 0 | 0 | — |
case-19 | fail→pass | 16,760 | 13,140 | -22% | 1 | 1 | 0% | 3,173 | 3,251 | +2% | 0 | 0 | — |
case-20 | fail→pass | 12,746 | 9,146 | -28% | 1 | 1 | 0% | 2,434 | 2,613 | +7% | 0 | 0 | — |
case-21 | fail→pass | 8,822 | 5,990 | -32% | 1 | 1 | 0% | 1,693 | 2,054 | +21% | 0 | 0 | — |
case-22 | fail→pass | 9,999 | 5,971 | -40% | 1 | 1 | 0% | 1,730 | 2,045 | +18% | 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. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 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.