AIMS ISO 42001 Forcing Questions — Security & Safety

This skill runs a six-question forcing interrogation on an AI Management System (AIMS) against ISO/IEC 42001, before certification audits, internal audit cycles, or new AI system onboarding. It produces a structured audit report with gap analysis, risk register status, audit plan, cross-framework reuse, and a readiness verdict.

compliance-os claude-code

📂 View skill on GitHub ↗ 🚀 How to use

✨ What it does

Checks AIMS scope statement for completeness of AI systems
Verifies AI policy includes lawful use, beneficial purpose, human oversight, and continual improvement
Assesses risk register coverage and mapping to Annex A controls
Ensures risk assessment re-run after material model changes
Validates Clause 9.2 internal audit plan and auditor independence
Evaluates integration with ISMS/QMS to avoid parallel systems

🎯 When to use it

Before stage 1 ISO 42001 certification audit
Before annual internal audit cycle (Clause 9.2)
When onboarding a new AI system into existing AIMS scope
When AI risk register hasn't been refreshed in > 6 months
After material model change (re-evaluate risks per Clause 6.1.2)

🚀 How to use

Trigger: /cs:aims-audit

Trigger with the slash command /cs:aims-audit <scope>, where describes the AI system or AIMS scope to audit. The skill expects evidence files (e.g., evidence.json, risks.json, audit_scope.json) and runs scripts for gap analysis, risk register, and audit scheduling. Example prompts:

/cs:aims-audit customer-support-chatbot

Run AIMS audit for our new recommendation engine before stage 1 certification.

📄 Output: A markdown audit report with gap analysis, risk register summary, Clause 9.2 audit plan, cross-framework reuse, verdict, and top 3 actions.

📦 Add this skill to Claude Code

# 1. Get the skills repo
git clone --depth 1 https://github.com/alirezarezvani/claude-skills /tmp/claude-skills

# 2. Copy this skill into your project (or ~/.claude/skills for all projects)
mkdir -p .claude/skills
cp -r /tmp/claude-skills/compliance-os/skills/aims-audit .claude/skills/aims-audit

Skill source: compliance-os/skills/aims-audit/SKILL.md

⚠️ Good to know

Requires access to the referenced scripts and evidence files; assumes ISO 42001 context and may need integration with other skills for full multi-framework view.

❓ FAQ

What are the six forcing questions?

The six questions cover: scope statement completeness, AI policy commitments, risk register coverage and control mapping, risk assessment re-run after material changes, Clause 9.2 audit plan and independence, and integration with ISMS/QMS.

When should I run this skill?

Run it before stage 1 certification, before annual internal audits, when onboarding new AI systems, if the risk register is stale, or after material model changes.

What output does it produce?

It produces a markdown audit report with sections for gap analysis, risk register, audit plan, cross-framework reuse, verdict, and top actions.

🤖 Overview, features, install steps and FAQ were generated from the project's SKILL.md on Sep 4, 2026. Always check the original source before running commands.