SKILLEMALL.ai
GitHub ↗ RU Sign in

CC nis2-directive-specialist

NIS2 Directive (EU 2022/2555) compliance for critical infrastructure entities, covering the 10 minimum security measures. Use for NIS2 compliance assessments, entity scope analysis, supply chain security, and incident reporting readiness.

borghei/Claude-Skills Agent Skills author: borghei 5 files · 2 scripts body ≈ 7 955 tokens Open the sourcegithub.com↗ analyzed 7 h ago

NIS2 Directive (EU 2022/2555) compliance for critical infrastructure entities, covering the 10 minimum security measures.

As a process C 55/100 · Has gaps — References files that are not bundled: ../information-security-manager-iso27001/, ../infrastructure-compliance-auditor/, ../dora-compliance-expert/

AnalyzerSecurityInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
80/100
safety, quality, tests
Safety 60%
86
Quality 40%
70
Run on models
none yet
Process rating
C
55/100
Has gaps
References files that are not bundled: ../information-security-manager-iso27001/, ../infrastructure-compliance-auditor/, ../dora-compliance-expert/
Tools and files w 18
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 14

✓ No critical or high findings

Medium and low: 14
  • low Risky intent intent-offensive-security references/nis2-implementation-playbook.md:75
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | 2 | Create incident playbooks (ransomware, data breach, DDoS, supply chain) | Security | 4+ playbooks |
  • low Risky intent intent-offensive-security references/nis2-implementation-playbook.md:140
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | 3 | Commission external penetration test | Security | Pentest report |
  • low Risky intent intent-offensive-security references/nis2-implementation-playbook.md:170
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Penetration Tester** | External pentest | Engagement in month 11 | 4 |
  • low Risky intent intent-offensive-security references/nis2-implementation-playbook.md:176
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Medium (50-249 employees) | 1-2 dedicated | 3-5 part-time | Advisory, pentest |
  • low Risky intent intent-offensive-security references/nis2-implementation-playbook.md:177
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    | Large (250-999 employees) | 2-4 dedicated | 5-10 part-time | Advisory, MSSP, pentest |
    detector
  • low Risky intent intent-offensive-security references/nis2-requirements-guide.md:90
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Ransomware response playbook
  • low Risky intent intent-offensive-security references/nis2-requirements-guide.md:151
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Immutable backups for ransomware protection
  • low Risky intent intent-offensive-security references/nis2-requirements-guide.md:268
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Penetration testing
  • low Risky intent intent-offensive-security references/nis2-requirements-guide.md:288
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    3. **Implement penetration testing**
  • low Risky intent intent-offensive-security references/nis2-requirements-guide.md:289
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Annual external penetration test (network and web application)
  • low Risky intent intent-offensive-security SKILL.md:183
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Security testing (SAST, DAST, penetration testing)
  • low Risky intent intent-offensive-security SKILL.md:195
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Penetration testing program
  • low Risky intent intent-offensive-security SKILL.md:608
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | 11 | **Testing** | Incident response exercises, penetration testing, compliance validation |
  • low Risky intent intent-offensive-security SKILL.md:671
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Technical penetration testing or vulnerability scanning (use infrastructure-compliance-auditor for technical checks)

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7955 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../information-security-manager-iso27001/
  • warning missing-ref reference to a missing file: ../infrastructure-compliance-auditor/
  • warning missing-ref reference to a missing file: ../dora-compliance-expert/
  • warning missing-ref reference to a missing file: ../nist-csf-specialist/
  • warning missing-ref reference to a missing file: ../soc2-compliance-expert/
  • warning missing-ref reference to a missing file: ../isms-audit-expert/

Process rating: all ten parameters 55/100

Will not run. References files that are not bundled: ../information-security-manager-iso27001/, ../infrastructure-compliance-auditor/, ../dora-compliance-expert/
  • 0Tools and files. 6 referenced file(s) missing: ../information-security-manager-iso27001/, ../infrastructure-compliance-auditor/, ../dora-compliance-expert/
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 10 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 7955 tokens
  • 85Steps. 215 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 20 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 238: enough signal without eating the budget
  • +4Structure: 63 headings
  • +3Step-by-step instructions: 215 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.