iso13485-audit-prep

$npx mdskill add alirezarezvani/claude-skills/iso13485-audit-prep

**Command:** `/compliance-os:iso13485-audit-prep <scope>`

SKILL.md

.github/skills/iso13485-audit-prepView on GitHub ↗
---
name: "iso13485-audit-prep"
description: "/compliance-os: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."
---

# /compliance-os:iso13485-audit-prep — ISO 13485 QMS Forcing Questions

**Command:** `/compliance-os: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.

## When to Run

- Before annual Clause 8.2.4 internal audit
- Before MDR / FDA QSR alignment review (substantially harmonized post Feb 2026)
- Before new-device commercial launch (DHF closure audit)
- After significant CAPA closure event (effectiveness verification audit)
- Post-recall event (root cause + corrective action audit)
- Quarterly during regulatory submission preparation

## The Six QMS Questions

### 1. Pull three random DHFs. Are design verification + validation evidence complete?
**Most-cited finding area.**
- DHF must include: design plan + inputs + outputs + verification + validation + transfer + changes
- Sample stratified by product class (I, IIa, IIb, III per MDR)
- Reference `iso13485_audit_playbook.md` for the per-DHF checklist
- Verify traceability matrix from user needs through clinical evidence

### 2. Show me the last 5 CAPAs with effectiveness verification evidence.
**Second-most-cited finding area.**
- Containment / correction / corrective action distinction documented
- Root cause analysis depth: 5 Why minimum
- Effectiveness verification = measurable evidence, not "we updated the procedure"
- Closure approved by appropriate authority
- Repeat CAPAs across products = systemic issue trigger

### 3. When was process validation (IQ/OQ/PQ) last revalidated?
**Clause 7.5.6 — often stale.**
- Initial validation at process introduction
- Revalidation triggers: process change, equipment change, material change, periodic schedule
- Trend monitoring (SPC) where statistical techniques apply per Clause 8.4
- Cross-check with cs-fda-qsr-auditor for 21 CFR 820.75 alignment

### 4. Show me the risk management file for the highest-risk product.
**Clause 7.1 + ISO 14971:2019.**
- Risk management plan exists per product
- Hazard identification covers reasonable foreseeable misuse
- Risk control hierarchy applied: inherent safety > protective measures > information for safety
- Residual risk evaluated + accepted with rationale
- Post-production information feeds back into RMF
- For AI-enabled medical devices: layer ISO 42001 A.5 impact assessment on top

### 5. Show me post-market surveillance evidence — last 6 months.
**Clause 8.2.1 — high-stakes for MDR + FDA.**
- Customer complaint log + investigation closure
- Vigilance reports (serious incident / FSCA) submitted per applicable regulation
- Trend analysis evidence + management review input
- Post-market clinical follow-up (PMCF) for MDR high-risk devices
- MDR reports per 21 CFR 803 for US-marketed devices (cross-check with cs-fda-qsr-auditor)

### 6. Where's the management review evidence covering all Clause 5.6 inputs?
**Annual minimum; semi-annual for mature programs.**
- Required inputs per Clause 5.6.2: audit results, customer feedback, process performance, product conformity, status of preventive + corrective actions, follow-up from prior reviews, changes that could affect QMS, recommendations for improvement, regulatory requirements
- Outputs per Clause 5.6.3: improvement decisions, product requirement changes, resource needs
- Integrated review across frameworks (per `multi_framework_audit_playbook.md`) preferred

## Workflow

```bash
# 1. Audit programme optimization
python ${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/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 ${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/capa-officer/ tools

# 4. Risk management file review
# Route to ${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/risk-management-specialist/ tools
```

## Output Format

```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]
```

## Routing

- `/compliance-os:compliance-readiness` — for multi-framework view
- `/compliance-os:fda-qsr-audit-prep` — for FDA-specific overlay
- `/compliance-os:aims-audit` — for AI-enabled medical device ISO 42001 layer
- `/compliance-os:gdpr-audit-prep` — for personal-data overlap (clinical data, customer data)
- `/c-level-agents:cpo-review` — for executive product strategy decisions
- `/c-level-agents:decide` — to log the verdict

## Related

- Agent: [`cs-cqm-iso13485`](../../agents/cs-cqm-iso13485.md)
- Skill: [`qms-audit-expert`](${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/qms-audit-expert/SKILL.md)
- Playbook: [iso13485_audit_playbook.md](${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/qms-audit-expert/references/iso13485_audit_playbook.md)
- Adjacent: `../fda-qsr-audit-prep/`, `../aims-audit/`, `../compliance-readiness/`

---

**Version:** 1.0.0

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.