Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/cs:iso13485-audit-prep <scope> — ISO 13485 QMS audit 6-question forcing interrogation. Design controls + CAPA + post-market focused. Use before Clause 8.2.4 internal audit, MDR / FDA QSR alignment review, or product-launch DHF closure audit.
.claude/skills/alirezarezvani-iso13485-audit-prep/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 62% | 0% |
Command: /cs:iso13485-audit-prep <scope>
The ISO 13485 QMS auditor pressure-tests any medical-device QMS work. Six traceability-obsessed questions before any internal audit, MDR / FDA QSR review, or product launch.
Most-cited finding area.
iso13485_audit_playbook.md for the per-DHF checklistSecond-most-cited finding area.
Clause 7.5.6 — often stale.
Clause 7.1 + ISO 14971:2019.
Clause 8.2.1 — high-stakes for MDR + FDA.
Annual minimum; semi-annual for mature programs.
multi_framework_audit_playbook.md) preferredbash# 1. Audit programme optimization python ra-qm-team/skills/qms-audit-expert/scripts/audit_schedule_optimizer.py audit_scope.json # 2. Mock audit for readiness check python ../../skills/compliance-os/scripts/audit_simulator.py iso13485_scope.json # 3. CAPA system review # Route to ra-qm-team/skills/capa-officer/ tools # 4. Risk management file review # Route to ra-qm-team/skills/risk-management-specialist/ tools
markdown# ISO 13485 Audit Prep: <scope> **Date:** YYYY-MM-DD ## The Decision Being Made [programme-plan | DHF-closure | CAPA-health | post-market-trend | pre-cert | MDR-FDA-alignment] ## Design Control Status (sampled DHFs) - DHFs sampled: <list product IDs> - Verification evidence: pass/fail per DHF - Validation evidence: pass/fail per DHF - Clinical evidence (per MDR Annex XIV / FDA 510(k)): pass/fail - Traceability matrix complete: yes/no per DHF ## CAPA Health - CAPAs sampled: N - Root cause analysis depth: adequate/inadequate per CAPA - Effectiveness verification: complete/incomplete per CAPA - Aging CAPAs > 90 days: N - Repeat issues across products: <list> ## Process Validation Status - Validations on schedule: % - Stale validations (> 12 months since revalidation): <list> - Statistical techniques applied per Clause 8.4: yes/no ## Risk Management File Status - Sampled product RMFs: <list> - Post-production updates in last 12 months: <count per product> - Residual risk acceptance signed: yes/no ## Post-Market Surveillance - Complaint trending: stable/rising - MDR / vigilance reports filed timely: % - PMCF on schedule (where required): yes/no ## Management Review Status - Last review date: YYYY-MM-DD - Required Clause 5.6.2 inputs present: yes/no - Open action items past due: N ## Cross-Framework Impact - EU MDR alignment: clean / gaps in <list> - FDA QSR alignment (post-Feb 2026): substantially harmonized; FDA-specific overlays per cs-fda-qsr-auditor - ISO 42001 AIMS overlay (if AI-enabled device): pass/fail per Annex A ## Verdict 🟢 READY | 🟡 CLOSE-DHF-GAPS-FIRST | 🔴 NOT-READY ## Top 3 Actions [3 concrete next steps with owner + corrective-action timeline]
/cs:compliance-readiness — for multi-framework view/cs:fda-qsr-audit-prep — for FDA-specific overlay/cs:aims-audit — for AI-enabled medical device ISO 42001 layer/cs:gdpr-audit-prep — for personal-data overlap (clinical data, customer data)/cs:cpo-review — for executive product strategy decisions/cs:decide — to log the verdictcs-cqm-iso13485qms-audit-expert../fda-qsr-audit-prep/, ../aims-audit/, ../compliance-readiness/Version: 1.0.0
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→fail | 15,342 | 18,013 | +17% | 1 | 1 | 0% | 2,695 | 5,007 | +86% | 0 | 0 | — |
case-22 | pass→pass | 18,556 | 19,775 | +7% | 1 | 1 | 0% | 3,578 | 5,588 | +56% | 0 | 0 | — |
case-01 | fail→pass | 27,425 | 18,960 | -31% | 1 | 1 | 0% | 5,471 | 5,531 | +1% | 0 | 0 | — |
case-02 | fail→pass | 30,778 | 18,628 | -39% | 1 | 1 | 0% | 5,681 | 5,329 | -6% | 0 | 0 | — |
case-03 | fail→pass | 33,065 | 20,196 | -39% | 1 | 1 | 0% | 6,262 | 5,744 | -8% | 0 | 0 | — |
case-05 | pass→pass | 14,775 | 14,446 | -2% | 1 | 1 | 0% | 2,724 | 4,338 | +59% | 0 | 0 | — |
case-06 | pass→pass | 13,111 | 13,081 | -0% | 1 | 1 | 0% | 2,528 | 4,179 | +65% | 0 | 0 | — |
case-07 | pass→pass | 12,478 | 11,701 | -6% | 1 | 1 | 0% | 2,230 | 3,961 | +78% | 0 | 0 | — |
case-08 | pass→pass | 12,656 | 13,432 | +6% | 1 | 1 | 0% | 2,412 | 4,427 | +84% | 0 | 0 | — |
case-09 | fail→pass | 11,581 | 10,389 | -10% | 1 | 1 | 0% | 2,297 | 3,847 | +67% | 0 | 0 | — |
case-10 | fail→pass | 15,765 | 16,464 | +4% | 1 | 1 | 0% | 3,043 | 4,926 | +62% | 0 | 0 | — |
case-11 | fail→pass | 12,115 | 3,925 | -68% | 1 | 1 | 0% | 2,121 | 2,540 | +20% | 0 | 0 | — |
case-12 | fail→pass | 11,429 | 2,283 | -80% | 1 | 1 | 0% | 2,153 | 2,166 | +1% | 0 | 0 | — |
case-13 | fail→pass | 9,338 | 2,194 | -77% | 1 | 1 | 0% | 1,837 | 2,197 | +20% | 0 | 0 | — |
case-14 | pass→pass | 14,562 | 16,306 | +12% | 1 | 1 | 0% | 2,741 | 5,053 | +84% | 0 | 0 | — |
case-15 | pass→pass | 14,914 | 13,014 | -13% | 1 | 1 | 0% | 2,537 | 4,096 | +61% | 0 | 0 | — |
case-16 | pass→pass | 9,149 | 11,002 | +20% | 1 | 1 | 0% | 1,744 | 3,729 | +114% | 0 | 0 | — |
case-17 | pass→pass | 11,582 | 17,076 | +47% | 1 | 1 | 0% | 2,228 | 4,981 | +124% | 0 | 0 | — |
case-18 | fail→pass | 14,723 | 12,157 | -17% | 1 | 1 | 0% | 2,676 | 4,063 | +52% | 0 | 0 | — |
case-19 | pass→pass | 18,896 | 15,976 | -15% | 1 | 1 | 0% | 3,552 | 4,716 | +33% | 0 | 0 | — |
case-20 | pass→fail | 16,784 | 19,094 | +14% | 1 | 1 | 0% | 3,392 | 5,420 | +60% | 0 | 0 | — |
case-21 | pass→pass | 17,802 | 15,434 | -13% | 1 | 1 | 0% | 3,296 | 4,628 | +40% | 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 +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.