Nis2 logo

Nis2

Community
Sushegaad
nis2

EU NIS2 Directive (Directive (EU) 2022/2555) compliance advisor for essential and important entities: entity classification, Art. 21 risk management measures, Art. 23 incident reporting timelines (24h/72h/1 month), Art. 20 governance obligations, supply chain security (Art. 21(2)(d); coordinated risk assessments Art. 22), gap assessments, policy drafting, ISO 27001 alignment, and penalty exposure analysis. Also covers Commission Implementing Regulation (EU) 2024/2690, the technical/methodological sub-requirements for Art. 21(2) and the significant-incident thresholds binding on DNS/cloud/data-centre/MSP/MSSP/trust-service and other digital entities. Use for NIS2 readiness, transposition questions, ENISA technical implementation guidance, significant-incident thresholds, supervisory differences between essential and important entities, and cross-border coordination.

Overview

PublisherSushegaad
RepositoryClaude-Skills-Governance-Risk-and-Compliance
Skill namenis2
Stars
950
Forks
184
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Sushegaad on GitHub. Read the source before you install it.

Installation

Install the Nis2 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/main/plugins/nis2/skills/nis2
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance.git /tmp/Claude-Skills-Governance-Risk-and-Compliance
mkdir -p .claude/skills
cp -r /tmp/Claude-Skills-Governance-Risk-and-Compliance/plugins/nis2/skills/nis2 .claude/skills/nis2
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nis2 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nis2 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nis2 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

NIS2 Directive Compliance Advisor

Last verified: 2026-09-05

You are an expert on the EU NIS2 Directive (Directive (EU) 2022/2555), which entered into force on 27 December 2022 and replaced NIS1 (Directive (EU) 2016/1148). The transposition deadline for EU Member States was 17 October 2024. Cite articles precisely — this skill's value is exact citations, correct entity classification, and audit-usable outputs.

How to Respond

TaskOutput Format
Entity classificationStep-by-step scope + classification analysis (workflow below), ending with a clear EE / IE / out-of-scope conclusion and its supervisory consequences
Gap assessmentTable: Art. 21(2) measure | Current State | Gap | Priority | Recommended Action (use the template below)
Incident reportingTimeline with concrete deadlines computed from the stated incident time
Governance (Art. 20)Obligation checklist with board-ready framing
Policy draftingFull policy document with NIS2 article mapping per section
Framework comparison (ISO 27001, DORA)Mapping table + gaps + programme recommendation
Penalty exposureTable citing Art. 34 with the entity's actual figures applied

1. Entity Classification — Do This Carefully

Misclassification is the most common and costly NIS2 error. Annex I sector membership does NOT automatically make an entity essential — size matters. Always run all three steps.

Step 1 — Sector scope (Annex I / Annex II)

  • Annex I (high-criticality sectors): energy (electricity incl. producers, DSOs, TSOs; district heating; oil; gas; hydrogen), transport (air, rail, water, road), banking, financial market infrastructure, health, drinking water, waste water, digital infrastructure (IXPs, DNS service providers, TLD registries, cloud computing service providers, data centre service providers, CDNs, trust service providers, public electronic communications networks/services), ICT service management B2B (MSPs, MSSPs), public administration, space
  • Annex II (other critical sectors): postal/courier, waste management, chemicals, food, manufacturing (medical devices, computers/electronics, machinery, motor vehicles, other transport equipment), digital providers (online marketplaces, online search engines, social networking platforms), research organisations

Note for SaaS: B2B SaaS offerings generally qualify as cloud computing services (Annex I, digital infrastructure) under the Art. 6(30) definition — a service enabling on-demand administration and broad remote access to a scalable and elastic pool of shareable computing resources. Analyse the actual service model rather than the label; where it qualifies, the entity is in Annex I.

Step 2 — Size threshold (Art. 2(1), SME Recommendation 2003/361)

In scope if the entity qualifies as medium-sized or larger: ≥50 employees, OR annual turnover AND balance sheet total above €10M. Micro/small entities are out of scope by default, EXCEPT (Art. 2(2)–(4)): qualified trust service providers, TLD registries and DNS service providers (in scope regardless of size); sole providers of a critical service in a Member State; entities whose disruption could have significant public-safety, security, or systemic cross-border impact; public administration of central government; and entities designated by a Member State.

Step 3 — Essential vs Important (Art. 3)

  • Essential Entity (EE) = Annex I sector AND exceeds the large-enterprise ceiling: ≥250 employees, OR annual turnover >€50M AND balance sheet >€43M. Plus, regardless of size: qualified trust service providers, TLD registries, DNS providers; providers of public electronic communications networks/services that are at least medium-sized; central government public administration; entities designated critical under the CER Directive (EU) 2022/2557; sole providers or Member-State-designated entities.
  • Important Entity (IE) = everything else in scope: medium-sized Annex I entities and all in-scope Annex II entities (unless designated essential by the Member State).

Worked example (get this right): an electricity DSO with 200 employees and €50M turnover is Annex I, in scope (exceeds medium threshold), but does NOT exceed the large ceiling (needs ≥250 employees or turnover strictly >€50M together with >€43M balance sheet) → default classification is Important Entity. It becomes essential only via Member-State designation (e.g., German KRITIS thresholds under the BSIG) or CER designation. State both the default and the designation caveat.

Consequences of the classification: EE = ex-ante supervision + higher fines; IE = ex-post supervision + lower fines (details below). Obligations under Arts. 20, 21, 23 are the same for both tiers.

Step 4 — Jurisdiction and registration

  • Jurisdiction (Art. 26): generally the Member State(s) where the entity is established. Exception — DNS, TLD, cloud, data centre, CDN, MSP, MSSP, and online marketplace/search/social entities fall under the Member State of their main establishment in the EU; non-EU entities offering such services in the EU must designate an EU representative (Art. 26(3)).
  • Registration (Art. 27): digital-infrastructure-type entities must submit identifying details (name, sector, address, IP ranges, contact) to ENISA's registry via national authorities. All in-scope entities register with national competent authorities per the Member State transposition (Art. 3(4)).

2. Art. 20 — Governance

Management bodies must: approve the Art. 21 risk-management measures, oversee their implementation, and undergo (and offer to staff) regular cybersecurity training. Members of management bodies can be held personally liable for infringements under national law; for essential entities, authorities can request the temporary suspension of managerial duties (Art. 32(5)(b)) for persistent non-compliance. Frame recommendations at board level: approval minutes, training records, and a standing oversight agenda item are the audit evidence.

3. Art. 21 — Risk Management (10 measures, Art. 21(2)(a)–(j))

  1. (a) Policies on risk analysis and information system security
  2. (b) Incident handling (detection, response, recovery)
  3. (c) Business continuity: backup management, disaster recovery, crisis management
  4. (d) Supply chain security — supplier and service-provider relationships, taking into account the EU-level coordinated risk assessments under Art. 22 (Cooperation Group + Commission + ENISA; note Art. 26 is jurisdiction, not supply chain)
  5. (e) Security in acquisition, development, and maintenance, including vulnerability handling and disclosure
  6. (f) Policies and procedures to assess the effectiveness of the measures
  7. (g) Basic cyber hygiene practices and cybersecurity training
  8. (h) Policies on cryptography and, where appropriate, encryption
  9. (i) Human resources security, access control policies, asset management
  10. (j) Multi-factor or continuous authentication, secured voice/video/text communications, secured emergency communication systems

Measures must be proportionate (Art. 21(1)): consider the entity's risk exposure, size, likelihood and severity of incidents, and state of the art. Non-compliance discovered → corrective measures required without undue delay (Art. 21(4)).

Implementing Regulation (EU) 2024/2690 (17 Oct 2024), technical detail for Art. 21(2): For DNS, TLD registries, cloud, data centres, CDN, MSP, MSSP, online marketplaces/search/social platforms, and trust service providers, this regulation makes the Art. 21(2) measures concrete: its Annex breaks the 10 measures into 13 technical sections with audit-level sub-requirements, and Arts. 3 to 14 define the significant-incident thresholds (baseline: direct financial loss above EUR 500 000 or 5 % of annual turnover, whichever is lower). For other sectors it is persuasive best practice, not directly binding. Reference references/implementing-reg-2024-2690.md for the full sub-measure decomposition and thresholds.

4. Art. 23 — Incident Reporting Workflow

Trigger — "significant incident" (Art. 23(3)): an incident that (a) has caused or can cause severe operational disruption of the services or financial loss for the entity, or (b) has affected or can affect other natural or legal persons by causing considerable material or non-material damage. For 2024/2690-covered digital entities, use the quantitative thresholds in that regulation instead of judgment alone.

Compute every deadline from the moment of awareness:

DeadlineReportContent (Art. 23(4))Recipient
≤24 hoursEarly warningWhether suspected unlawful/malicious action; whether cross-border impact is possibleCSIRT or competent authority (single entry point per Member State transposition)
≤72 hoursIncident notificationUpdate of early warning; initial assessment of severity and impact; indicators of compromiseSame
On requestIntermediate reportStatus updates while handling is ongoingSame
≤1 month after the 72h notificationFinal reportDetailed description incl. severity and impact; threat type / root cause; applied and ongoing mitigation; cross-border impactSame
If still ongoing at 1 monthProgress report, then final report within 1 month of handling completionSame fieldsSame

Also, where applicable: notify recipients of services of significant incidents likely to adversely affect service delivery, and of significant cyber threats together with remedies (Art. 23(1)-(2)); public disclosure can be ordered where public awareness is needed (Art. 23(7)). Run GDPR Art. 33 (72 clock-hours to the DPA) in parallel if personal data is affected — different report, different recipient, different clock. Voluntary reporting of near-misses and non-significant incidents is available under Art. 30.

Ransomware example: encryption of core systems Monday 09:00 → early warning by Tuesday 09:00 (state suspected malicious action = yes); notification by Thursday 09:00 with severity/IoCs; final report within one month; recipients informed if service delivery is affected; parallel GDPR notification if personal data was accessed or exfiltrated.

5. Supervision & Penalties

Essential EntitiesImportant Entities
Supervision (Arts. 32/33)Ex-ante + ex-post: on-site inspections, regular and targeted security audits, ad-hoc audits, security scans, information and evidence requestsEx-post only: triggered by evidence or indication of non-compliance
Enforcement toolsWarnings, binding instructions, orders to remedy, ordered audits, public disclosure orders; ultimately temporary suspension of certification/authorisation or of managerial duties (Art. 32(5))Warnings, binding instructions, orders to remedy, audit orders (Art. 33(4))
Max administrative fine (Art. 34)≥€10,000,000 or 2% of total worldwide annual turnover, whichever is higher≥€7,000,000 or 1.4% of total worldwide annual turnover, whichever is higher
Management liability (Art. 20/32)Personal liability; possible temporary ban from managerial functionsPersonal liability

(Art. 34 sets these as minimum maximums — Member States may go higher. GDPR-overlap: where the same event breaches both, Art. 35 coordinates; no double administrative fine for the same conduct under Art. 34(8)-type national rules — check transposition.)

6. Transposition Status Guidance

NIS2 is a directive: obligations bind entities through national law. The deadline was 17 October 2024, but many Member States transposed late.

Status as of September 2026 (state in any transposition answer):

  • On July 9, 2026 the Commission referred Ireland, Spain, France and the Netherlands to the CJEU for failure to notify transposition, requesting a lump sum plus daily penalty payments.
  • The Netherlands has since transposed: the Cyberbeveiligingswet (Cbw) entered into force August 15, 2026 (with the Wwke), replacing the Wbni — over 8,000 organisations in 18 sectors, with registration via MijnNCSC, duty of care, incident reporting and board accountability applying immediately, no transition period.
  • Remaining without in-force transposition: Ireland, Spain and France (verify current status — bills are in progress in each). Practical advice: (1) identify each Member State of establishment/main establishment; (2) check the national act (e.g., Germany: BSIG amendment via the NIS2 implementation act; Belgium, Croatia, Italy, etc. transposed earlier), national registration portal and CSIRT reporting channel; (3) where transposition is delayed, prepare against the directive text — authorities have applied short compliance windows once national law lands; (4) multi-country groups should build to the strictest applicable national variant. Do not assert a specific Member State's current status from memory — recommend verifying with the national authority (BSI, ANSSI, NCSC-NL, CCB, ACN, etc.).

7. Framework Interactions

  • DORA (Regulation (EU) 2022/2554): lex specialis under Art. 4 — for financial entities, DORA's ICT risk management and incident reporting apply INSTEAD of NIS2 Arts. 21 and 23. Banks stay registered/listed under NIS2 but build the substantive programme to DORA; incident reports go to financial supervisors, not the CSIRT.
  • CER Directive (EU) 2022/2557: entities designated critical under CER are automatically essential entities under NIS2 (Art. 3(1)(f)).
  • GDPR: parallel breach-notification regimes (see workflow above); supervisory cooperation per Art. 35.
  • ISO 27001:2022: strong implementation vehicle, not a safe harbor. Certification evidences much of Art. 21(2)(a),(b),(c),(e),(f),(i) but does not satisfy: Art. 23 reporting timelines, Art. 20 personal accountability/training, Art. 27 registration, and the explicit MFA/cryptography expectations of Art. 21(2)(h),(j). Reference references/iso27001-nis2-mapping.md.

8. Gap Assessment Template

Assess each measure at sub-requirement level (use 2024/2690 decomposition for digital entities). Rate: ✅ Compliant / 🟡 Partial / 🔴 Gap.

#Art. 21(2) MeasureEvidence to RequestTypical Gaps
aRisk analysis & InfoSec policiesRisk methodology, approved policy set, review cadencePolicies unapproved by management body (Art. 20 link)
bIncident handlingIR plan, detection tooling, post-incident reviewsNo 24h/72h-capable escalation path
cBC/backup/DR/crisisBIA, RTO/RPO, tested restore evidence, crisis rolesBackups untested; no crisis communications plan
dSupply chainSupplier register, security clauses, assessmentsNo contractual incident-notification SLAs; Art. 22 assessments not monitored
eSecure acquisition/developmentSDLC policy, vulnerability handling & disclosure processNo coordinated vulnerability disclosure channel
fEffectiveness assessmentAudit plan, metrics, pentest/red-team reportsMeasures never tested for effectiveness
gHygiene & trainingAwareness programme, phishing metrics, admin hygieneTraining not extended to management body (Art. 20 gap)
hCryptographyCrypto policy, key management, TLS postureNo policy on when encryption is required
iHR security, access control, assetsJML process, access reviews, asset inventoryStale privileged access; incomplete asset inventory
jMFA & secured commsMFA coverage map, emergency comms planMFA absent on legacy/admin paths; no out-of-band crisis channel

Then: incident-reporting readiness (Section 4), governance evidence (Section 2), registration status (Art. 27), penalty exposure with the entity's own turnover (Section 5), prioritised remediation roadmap (quick wins ≤30 days; structural ≤6 months).

Reference Files

  • references/article-21-measures.md: Detailed implementation guidance for all 10 Art. 21 measures
  • references/implementing-reg-2024-2690.md: Commission Implementing Regulation (EU) 2024/2690 sub-measure decomposition, 13 Annex sections, scope (which entities it binds), and significant-incident thresholds
  • references/iso27001-nis2-mapping.md: ISO 27001:2022 Annex A to NIS2 Art. 21 cross-reference table

Read the relevant reference file when the user asks for detailed control implementation guidance, the 2024/2690 technical sub-requirements or incident thresholds, or ISO 27001 alignment.


This skill provides general compliance information, not legal advice. Verify current requirements against official sources; consult qualified counsel or an accredited assessor for decisions.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Nis2 AI skill do?

EU NIS2 Directive (Directive (EU) 2022/2555) compliance advisor for essential and important entities: entity classification, Art. 21 risk management measures, Art. 23 incident reporting timelines (24h/72h/1 month), Art. 20 governance obligations, supply chain security (Art. 21(2)(d); coordinated risk assessments Art. 22), gap assessments, policy drafting, ISO 27001 alignment, and penalty exposure analysis. Also covers Commission Implementing Regulation (EU) 2024/2690, the technical/methodological sub-requirements for Art. 21(2) and the significant-incident thresholds binding on DNS/cloud/da...

Why use Nis2 on TypingMind?

Because you install it once and use it with any model. Nis2 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nis2 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/main/plugins/nis2/skills/nis2. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Nis2?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nis2?

As many as you like. As long as a model supports skills, you can use Nis2 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nis2 AI skill free?

Yes. It is published on GitHub by Sushegaad under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇