AIMS ISO 42001 Audit Check
Pressure-tests your ISO/IEC 42001 AI Management System with six forcing questions and outputs a certification-readiness verdict.
Security & ReviewAdvanced★ 24,151⑂ 3,405AI score 7/10Last updated: Aug 9, 2026
What it does
Invoke /cs:aims-audit <scope> and an ISO/IEC 42001 AIMS specialist interrogates your AI management system with six forcing questions before any certification commitment, internal audit cycle, or new-system onboarding.
- Scope completeness: does the Clause 4.3 statement name every AI system, including embedded models, third-party AI services, and "experimental" production systems?
- AI policy four commitments: lawful use, beneficial purpose, human oversight, continual improvement — missing any is a critical stage-1 nonconformity
- Risk register ↔ Annex A mapping: every high/critical risk must link to at least one control (Clause 6.1.3)
- Re-assessment after material model change: retraining, fine-tuning, architecture or deployment-context change all count
- Clause 9.2 audit plan and auditor independence across a rolling 3-year cycle
- ISMS/QMS integration: parallel systems cost ~5x to maintain; ~60% of Clause 4-10 evidence can be reused from ISO 27001 / 13485
It produces a Markdown report with gap analysis, risk summary, audit-plan coverage, cross-framework reuse percentages, a 🟢/🟡/🔴 verdict, and three concrete next actions with owners and dates.
Who it's for
- Compliance and quality leads preparing for an ISO 42001 stage-1 audit
- Internal auditors building a Clause 9.2 audit programme
- AI governance leads onboarding a new AI system into an existing AIMS scope
- CISOs and QA managers integrating AIMS with ISO 27001 or ISO 13485 to cut duplication
Examples
- Stage-1 prep:
/cs:aims-audit company-wide AIMS→ weighted Clause 4-10 coverage, critical gap list,not_readyverdict, and three prioritised fixes - New system onboarding: adding an internal chatbot surfaces missing scope wording, unregistered risks, and unmapped Annex A controls in one pass
- Post-fine-tune review: checks whether an 18-month-old risk assessment still satisfies Clause 6.1.2 and defines what must be re-run
· · · Install guide · · ·
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the .gemini/skills/aims-audit folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/aims-audit/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/alirezarezvani/claude-skills.git && mkdir -p ~/.claude/skills/aims-audit && cp -r claude-skills/.gemini/skills/aims-audit/* ~/.claude/skills/aims-audit/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and move to your working directory.
- Clone the repository:
git clone https://github.com/alirezarezvani/claude-skills.git - Create the skill folder:
mkdir -p ~/.claude/skills/aims-audit - Copy the files:
cp -r claude-skills/.gemini/skills/aims-audit/* ~/.claude/skills/aims-audit/ - The skill references Python scripts under
ra-qm-team/skills/iso42001-specialist/scripts/andskills/compliance-os/, so copy those folders too or run commands from the cloned repo root. - Restart Claude Code and try
/cs:aims-audit our company AIMS scope. - Running the scripts requires Python 3 plus input files such as
evidence.json,risks.json, andaudit_scope.json. If you don't have them, ask Claude for the expected schema first.
View source on GitHub ↗License: MIT