Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/cs:fda-qsr-audit-prep <scope> — FDA 21 CFR 820 (QSR / QMSR) audit 6-question forcing interrogation. Post-Feb 2026 substantially harmonized with ISO 13485. Use before annual internal QSR audit, pre-FDA-inspection readiness, or Form 483 response.
.claude/skills/alirezarezvani-fda-qsr-audit-prep/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 91% | 0% |
Command: /cs:fda-qsr-audit-prep <scope>
The FDA QSR auditor pressure-tests any US medical-device QSR work. Six questions before any internal audit, FDA inspection, Form 483 response, or recall decision.
21 CFR 820.198 + 21 CFR 803 — most-cited FDA inspection area.
Cross-walks ISO 13485 Clause 7.5.6 (substantially harmonized post-Feb 2026).
21 CFR 820.180 — 2-year retention from commercial distribution; check sampling for completeness.
21 CFR 820.100 = ISO 13485 8.5.2 substantially harmonized.
FDA-specific overlay not in ISO 13485.
Form 483 = FDA observation; not equivalent to ISO nonconformity.
bash# 1. QSR compliance posture python ra-qm-team/skills/fda-consultant-specialist/scripts/qsr_compliance_checker.py compliance_state.json # 2. FDA submission tracking (510(k) / PMA / IDE) python ra-qm-team/skills/fda-consultant-specialist/scripts/fda_submission_tracker.py submissions.json # 3. HIPAA overlap (if connected device handles PHI) python ra-qm-team/skills/fda-consultant-specialist/scripts/hipaa_risk_assessment.py phi_inventory.json # 4. Mock FDA inspection python ../../skills/compliance-os/scripts/audit_simulator.py fda_qsr_scope.json
markdown# FDA QSR Audit Prep: <scope> **Date:** YYYY-MM-DD ## The Decision Being Made [programme-plan | inspection-readiness | 483-response | MDR-decision | recall] ## Complaint + MDR Posture - Complaints last quarter: N - MDR-reportable events: M - MDR reports filed within timeline: % (target 100%) - Complaint trending review at management level: yes/no ## Process Validation Status (21 CFR 820.75) - Validations on schedule: % - Stale validations: <list> - Statistical techniques applied: yes/no per process ## DHR Completeness (21 CFR 820.180) - DHRs sampled: N - Completeness rate: % - 2-year retention compliant: yes/no - Stratified by product class: yes/no ## CAPA Health (21 CFR 820.100) - CAPAs sampled: N - Root cause analysis depth: adequate/inadequate - Effectiveness verification: complete/incomplete - Aging CAPAs > 90 days: N ## Labeling (21 CFR 801) - Recent products reviewed: <list> - Labeling accurate + non-misleading: yes/no - UDI compliance per 21 CFR 830: yes/no ## Form 483 / Warning Letter History - Form 483s last 3 years: N (each: closed/in-progress) - Warning Letters last 5 years: N (each: closed/in-progress) - Pattern across observations: <thematic> ## ISO 13485 Cross-Walk (post-Feb 2026 harmonization) - ISO 13485 audit findings: <link to cs-cqm-iso13485 output> - FDA-specific overlays remaining: labeling + complaint handling + MDR reporting + recall procedures - Cross-framework reuse: % of evidence shared ## Verdict 🟢 INSPECTION-READY | 🟡 GAPS-IDENTIFIED | 🔴 NOT-READY ## Top 3 Actions [3 concrete next steps with owner + FDA-cited timeline (15 days / 30 days / etc.)] ## Outside Counsel Required [For Warning Letter response, recall decisions, or 510(k) / PMA strategy disputes]
/cs:compliance-readiness — for multi-framework view/cs:iso13485-audit-prep — for ISO 13485 cross-walk pair (substantially harmonized)/cs:gdpr-audit-prep — if connected device handles personal data/cs:gc-review — for Warning Letter response coordinationcs-fda-qsr-auditorfda-consultant-specialist../iso13485-audit-prep/, ../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-13 | fail→pass | 13,668 | 16,831 | +23% | 1 | 1 | 0% | 2,478 | 4,920 | +99% | 0 | 0 | — |
case-01 | fail→fail | 30,869 | 26,226 | -15% | 1 | 1 | 0% | 5,517 | 6,473 | +17% | 0 | 0 | — |
case-02 | fail→fail | 33,254 | 24,803 | -25% | 1 | 1 | 0% | 6,259 | 6,235 | -0% | 0 | 0 | — |
case-03 | fail→fail | 32,882 | 23,274 | -29% | 1 | 1 | 0% | 6,272 | 5,741 | -8% | 0 | 0 | — |
case-04 | pass→pass | 24,750 | 24,057 | -3% | 1 | 1 | 0% | 4,280 | 5,799 | +35% | 0 | 0 | — |
case-05 | fail→fail | 19,330 | 24,088 | +25% | 1 | 1 | 0% | 3,294 | 6,132 | +86% | 0 | 0 | — |
case-06 | fail→fail | 27,699 | 32,929 | +19% | 1 | 1 | 0% | 5,112 | 7,910 | +55% | 0 | 0 | — |
case-07 | pass→pass | 13,617 | 16,205 | +19% | 1 | 1 | 0% | 2,462 | 4,751 | +93% | 0 | 0 | — |
case-08 | pass→pass | 12,281 | 11,640 | -5% | 1 | 1 | 0% | 2,278 | 3,923 | +72% | 0 | 0 | — |
case-09 | pass→pass | 13,166 | 13,995 | +6% | 1 | 1 | 0% | 2,624 | 4,604 | +75% | 0 | 0 | — |
case-10 | pass→pass | 13,324 | 10,324 | -23% | 1 | 1 | 0% | 2,224 | 3,576 | +61% | 0 | 0 | — |
case-11 | fail→pass | 14,909 | 11,776 | -21% | 1 | 1 | 0% | 2,562 | 3,932 | +53% | 0 | 0 | — |
case-12 | pass→pass | 16,081 | 18,538 | +15% | 1 | 1 | 0% | 2,870 | 4,961 | +73% | 0 | 0 | — |
case-14 | pass→pass | 12,790 | 13,879 | +9% | 1 | 1 | 0% | 2,370 | 4,389 | +85% | 0 | 0 | — |
case-15 | fail→pass | 25,433 | 33,611 | +32% | 1 | 1 | 0% | 4,700 | 7,957 | +69% | 0 | 0 | — |
case-16 | fail→pass | 18,334 | 18,146 | -1% | 1 | 1 | 0% | 3,304 | 5,196 | +57% | 0 | 0 | — |
case-17 | pass→pass | 13,835 | 16,722 | +21% | 1 | 1 | 0% | 2,717 | 5,058 | +86% | 0 | 0 | — |
case-18 | fail→pass | 13,627 | 15,688 | +15% | 1 | 1 | 0% | 2,497 | 4,762 | +91% | 0 | 0 | — |
case-19 | pass→pass | 11,118 | 15,200 | +37% | 1 | 1 | 0% | 2,129 | 4,484 | +111% | 0 | 0 | — |
case-20 | fail→pass | 27,040 | 18,375 | -32% | 1 | 1 | 0% | 4,912 | 5,088 | +4% | 0 | 0 | — |
case-21 | fail→pass | 22,519 | 16,614 | -26% | 1 | 1 | 0% | 4,561 | 4,910 | +8% | 0 | 0 | — |
case-22 | fail→pass | 22,754 | 11,398 | -50% | 1 | 1 | 0% | 4,095 | 3,966 | -3% | 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 +36 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.