LLM ISO 27001 skill
An ISO 27001 security management template in Markdown and git: an agent runs policies, registers and executable control checks.
- 66 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent edits template documents and registers and runs checks, and company data reaches the model.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/llm-iso-27001Detects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent edits template documents and registers and runs checks, and company data reaches the model.
This is third-party code. Review the repository files before installing.
What it does
LLM ISO 27001 is a template repository for an information security management system. It holds policies and procedures, working logs and registers, and an executable check for each suitable control. `statement_of_applicability.md` maps 93 controls to implementation status and the covering document. Optional overlays: ISO 42001 for AI systems, EN 18286, NIS 2 with the French ReCyF transposition, and AIUC-1 for AI agent certification. The `operate-isms` skill teaches an agent to set up, review and update the system and run its checks. You copy the template on GitHub and start an agent such as `claude`. The agent replaces the fictional ACME CORP with your company, rewrites the policy to your context, fills the risk and supplier registers, extends the ISO 42001 overlay and runs the checks. Every change lands as a git commit, and a person approves the result.
Who it is for. Security and compliance specialists in small companies who build an ISO 27001 system and want an agent doing the routine under their control.
Good fit when
- A company prepares for ISO 27001 and needs a working set of policies, procedures and registers.
- A risk or supplier register has to be filled from the company and stack description.
- You need control checks that can run on a schedule and read as a report.
- An ISO 42001 layer is added to ISO 27001 because the company builds or uses AI systems.
Not a fit when
- You need to replace a security expert or auditor: the author calls the template an accelerator, not a replacement.
- You want ready certification with no manual review: every control starts marked as not assessed.
- Policies must live in a closed GRC platform with no git.
Example request
We are a French company of 40 people on cloud and SaaS. Replace ACME CORP with our name, rewrite the security policy and fill the risk register.Limitations
All 93 controls start as not assessed: nothing counts as done until you confirm it. The result stays a draft that a person reviews and signs off. The agent reads your company data, so do not give it facts that cannot be disclosed to a model. The template follows the standards in the author's own interpretation, and national NIS 2 requirements are shown for France. The demo ISMS of Mistral AI is built from public data and is not affiliated with the company.
How to disable. Delete the `skills/operate-isms` folder from the skills directory or the whole repository of your template copy. The change history stays in your copy's git.
FAQ
Where do I start with the template?
Click Use this template on GitHub, name the copy `my-company-isms`, clone it and start the agent in the root. Then describe the company and ask it to replace ACME CORP.
What is in the template?
Policies, procedures, a risk register, an incident log, working records, executable checks and a master applicability register of 93 controls.
Which standards are covered?
ISO 27001, with optional overlays for ISO 42001, EN 18286, NIS 2 with the French ReCyF transposition and AIUC-1.
Does the template replace a consultant?
No. The author calls it an accelerator: changes are visible, reversible and reviewed by a person.
Are special tools needed?
No. Everything is plain Markdown under git with no build step or closed formats.
Discussion
No questions or reviews yet.
Related
SkillsClaude Skills for GRC
Claude Skills for Governance, Risk & Compliance (GRC)
A set of governance, risk and compliance skills: ISO 27001, SOC 2, GDPR, HIPAA, PCI DSS, NIST, the EU AI Act and other frameworks
An open library of 65 governance, risk and compliance skills: the agent drafts and gathers, while people make the calls.
A CLI that records Claude Code, Codex and Cursor sessions, signs them on git push and checks them against Rego policies.
A set of skills that turns the agent into a static code analyzer: finds vulnerabilities and builds a prioritized report
A Claude Code and OpenCode plugin making an agent a compliance analyst: 18 frameworks, 24 commands, SSP, POA&M and policy review.
Cybersecurity Skills
Cybersecurity Skills for AI Agents
42 security skills for Claude Code, Cursor and Codex: code and cloud audits, authorization-gated pentesting and incident response
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| LLM ISO 27001 (this card) | no | 66 | |
| Claude Skills for GRC | no | 1,070 | a skill set across many standards; this is a ready ISMS with registers and checks under git |
| GRC Knowledge Plugin | no | 190 | an analyst plugin for 18 standards with commands and reviews; this is a template an agent runs as a repository |
README in short
The idea is inspired by Andrej Karpathy's note on an LLM wiki and the paper "Is Grep All You Need?". Everything is plain Markdown under git with no build step, so an agent can also use the tools you already have, such as Jira, Confluence or a GRC platform.
README badge
Original SKILL.md
--- name: operate-isms description: Operate an ISO 27001 / ISO 42001 / NIS 2 information security management system stored as markdown in this repository. Use when the user asks to instantiate, review, update, or run compliance checks against their ISMS, policies, risk register, or Statement of Applicability. license: MIT metadata: version: "1.0" --- # Operate the ISMS This repository is an ISO 27001 (+ISO 42001 +NIS 2) ISMS: policies, procedures, risk register, and a Statement of Applicability (SoA), all in markdown and versioned in git. ## Core rules - The SoA is the single source of truth for control coverage. Never mark a control implemented without a document behind it. - Git is the audit trail. Commit every change with a clear message. - This repository can be the system of record on its own — nothing else is required. When content already lives elsewhere (Confluence, Notion, Jira, Probo, CISO Assistant...), the agent can read it and reconcile it here — typically importing it so git becomes the source of truth, or leaving the external tool as the reference when that fits better. A deliberate choice, made per source, never assumed. - One source of truth per topic — extend existing documents rather than duplicating them. ## Checks Files under `checks/` (and framework-specific `checks/` subfolders) are executable verifications. Each reads its requirement from a policy or procedure — never hard-coded — and returns pass/fail. Run a check by reading its instructions and executing them against the real environment. See `AGENTS.md` at the repository root for the full operating rules.