iso27001-audit-prep

$npx mdskill add alirezarezvani/claude-skills/iso27001-audit-prep

**Command:** `/compliance-os:iso27001-audit-prep <scope>`

SKILL.md

.github/skills/iso27001-audit-prepView on GitHub ↗
---
name: "iso27001-audit-prep"
description: "/compliance-os:iso27001-audit-prep [scope] — ISO 27001 ISMS audit readiness 6-question forcing interrogation. Use before annual Clause 9.2 internal audit, surveillance audit prep, or stage 1 certification readiness."
---

# /compliance-os:iso27001-audit-prep — ISO 27001 ISMS Audit Forcing Questions

**Command:** `/compliance-os:iso27001-audit-prep <scope>`

The ISO 27001 ISMS auditor pressure-tests any ISMS work. Six sample-driven questions before any internal audit, stage 1 readiness, or surveillance audit.

## When to Run

- Before annual Clause 9.2 internal audit
- Before stage 1 / stage 2 ISO 27001 certification audit
- Before surveillance audit (year 2 / year 3)
- After material change to ISMS scope (new business unit, new product line, new SaaS adoption)
- Post-incident (breach triggers ad-hoc ISMS audit)
- Quarterly during high-growth phase

## The Six ISMS Questions

### 1. What's the audit scope, and is rolling 3-year coverage on track?
**No 3-year coverage discipline, no defensible programme.**
- Every Clause 4-10 + every applicable Annex A control must be audited at least once per 3-year cycle
- Run `isms_audit_scheduler.py` in `${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/isms-audit-expert/`
- Confirm auditor independence — no self-audit on any sample

### 2. When was the risk register last refreshed, and are treatments linked to Annex A controls?
**Stale risk register = certification finding.**
- Quarterly refresh expected; annual minimum
- Every high/critical risk must link to ≥ 1 Annex A control treating it
- Residual risk acceptance documented + signed
- Review against `iso27001_audit_playbook.md` for stage 1 expectations

### 3. Show me the access review records — quarterly cadence, the last 4 quarters.
**Most-cited finding area.**
- Annex A.5.15 + A.8.2 + A.8.3 access controls
- Sample real records pulled from Okta / IAM, not curated audit-prep packs
- For each terminated employee in last 90 days: deprovisioning evidence within 24-hour SLA
- Privileged access reviewed at finer granularity

### 4. What's the supplier inventory + last review evidence?
**Second-most-cited finding area.**
- Annex A.5.19-A.5.21 supplier management
- Critical SaaS suppliers reviewed at least annually
- DPAs signed for personal-data sub-processors (cross-check with cs-dpo-gdpr)
- AI-specific contract clauses where third-party AI services in use (cross-check with cs-aims-iso42001)

### 5. Where's the incident response evidence + post-incident review?
**A.5.24-27 + A.6.8 — high-stakes audit area.**
- Severity definitions documented + consistently applied
- Last 5 incidents have post-incident review (PIR) within 30-day SLA
- GDPR Article 33 / 34 notification timing aligned with A.5.24 (cross-check with cs-dpo-gdpr)
- Blameless retro culture; not punitive

### 6. What's the management review cadence + inputs?
**Clause 9.3 required inputs are prescriptive — easy to miss.**
- Required inputs: audit results, risks, performance, nonconformities, opportunities
- Schedule: annual minimum; quarterly preferred for mature programs
- Outputs documented + tracked to closure
- Integrated review across frameworks (per `multi_framework_audit_playbook.md`) preferred to separate reviews

## Workflow

```bash
# 1. Audit programme planning
python ${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/isms-audit-expert/scripts/isms_audit_scheduler.py audit_scope.json

# 2. Mock audit for readiness check
python ../../skills/compliance-os/scripts/audit_simulator.py iso27001_scope.json

# 3. Cross-framework reuse (SOC 2 = 75% overlap; ISO 42001 = 60% reuse)
python ../../skills/compliance-os/scripts/cross_framework_mapper.py program.json
```

## Output Format

```markdown
# ISO 27001 Audit Prep: <scope>
**Date:** YYYY-MM-DD

## The Decision Being Made
[programme-plan | finding-severity | cert-readiness | incident-followup]

## Audit Programme Status
- Clauses scheduled this year: <list>
- Annex A controls scheduled: <count>
- Rolling 3-year coverage: clean | gaps in <list>
- Auditor independence: clean | issues in <list>

## Risk Register Health
- Last refresh: YYYY-MM-DD
- High/critical risks without Annex A control link: N
- Residual risk acceptance documentation: complete | gaps

## High-Stakes Controls Status
- A.5.15 + A.8.2 + A.8.3 access control: pass/fail with sample
- A.5.19-A.5.21 supplier mgmt: pass/fail with sample
- A.5.24-27 + A.6.8 incident response: pass/fail with sample
- A.8.15-16 logging: pass/fail with sample

## Management Review Status
- Last review date: YYYY-MM-DD
- Required Article 9.3 inputs present: yes/no
- Open action items past due: N

## Cross-Framework Impact
- SOC 2 controls affected: <list>
- ISO 42001 controls affected (if applicable): <list>
- GDPR Article 32 controls affected: <list>

## Verdict
🟢 READY | 🟡 CLOSE-CRITICALS-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:soc2-audit-prep` — for SOC 2 cross-walk pair (75% overlap)
- `/compliance-os:aims-audit` — for ISO 42001 AIMS cross-walk
- `/compliance-os:gdpr-audit-prep` — for Article 32 organizational measures overlap
- `/c-level-agents:ciso-review` — for executive cybersecurity strategy
- `/c-level-agents:decide` — to log the verdict

## Related

- Agent: [`cs-ciso-iso27001`](../../agents/cs-ciso-iso27001.md)
- Skill: [`isms-audit-expert`](${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/isms-audit-expert/SKILL.md)
- Playbook: [iso27001_audit_playbook.md](${CLAUDE_PLUGIN_ROOT}/vendor/ra-qm-team/isms-audit-expert/references/iso27001_audit_playbook.md)
- Adjacent: `../soc2-audit-prep/`, `../aims-audit/`, `../gdpr-audit-prep/`, `../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.