SKILLEMALL.ai
GitHub ↗ RU Sign in

CC dora-compliance-expert

DORA (EU 2022/2554) digital operational resilience compliance for financial entities, covering all 5 pillars. Use for DORA readiness assessments, ICT risk management, incident classification, and third-party ICT oversight.

borghei/Claude-Skills Agent Skills author: borghei 9 files · 2 scripts body ≈ 1 850 tokens Open the sourcegithub.com↗ analyzed 8 h ago

DORA (EU 2022/2554) digital operational resilience compliance for financial entities, covering all 5 pillars.

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerInfrastructureSecurityData and analyticstype 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
86/100
safety, quality, tests
Safety 60%
82
Quality 40%
92
Run on models
none yet
Process rating
C
61/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Result and completion w 14
40
the three weakest of ten parameters · all ten

How to improve

    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 · 18

    ✓ No critical or high findings

    Medium and low: 18
    • low Risky intent intent-offensive-security references/dora-five-pillars-guide.md:209
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Penetration testing | Annual | Critical systems | All |
    • low Risky intent intent-offensive-security references/dora-five-pillars-guide.md:237
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Cyber attack scenarios (ransomware, APT, DDoS)
    • low Risky intent intent-offensive-security references/dora-five-pillars-guide.md:243
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. **Penetration testing**
    • low Risky intent intent-offensive-security references/dora-five-pillars-guide.md:244
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - External network penetration testing
    • low Risky intent intent-offensive-security references/dora-five-pillars-guide.md:245
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Web application penetration testing
    • low Risky intent intent-offensive-security references/dora-third-party-management.md:112
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
      | 14 | Participation in entity's TLPT (threat-led penetration testing) | 30(3)(e) | [ ] |
      table
    • low Risky intent intent-offensive-security references/five-pillars-detail.md:201
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | **Penetration testing** | Annual minimum | Simulated attack testing |
    • low Risky intent intent-offensive-security references/five-pillars-detail.md:203
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Advanced Testing — Threat-Led Penetration Testing (Article 26)
    • low Risky intent intent-offensive-security references/five-pillars-detail.md:220
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      3. **Red team phase:** Execute realistic attack scenarios against production systems
    • low Risky intent intent-offensive-security references/five-pillars-detail.md:222
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      5. **Purple team phase:** Collaborative exercises between red team (attackers) and blue team (defenders)
    • low Risky intent intent-offensive-security references/five-pillars-detail.md:234
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Collaborative exercise between red team and blue team
    • low Risky intent intent-offensive-security references/framework-overview.md:37
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Threat-led penetration testing (TLPT) methodology
    • low Risky intent intent-offensive-security references/implementation-and-infrastructure.md:20
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | 8 | **Advanced Testing** | Conduct penetration testing, scenario-based exercises, TLPT preparation (if applicable) |
    • low Risky intent intent-offensive-security references/implementation-and-infrastructure.md:71
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Immutable backup storage for ransomware resilience
    • low Risky intent intent-offensive-security references/implementation-and-infrastructure.md:92
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      | Resilience testing program scored as non-compliant | Only basic vulnerability scanning performed; no scenario-based or penetration testing | Design a comprehensive testing program per Article 25 cov
      detector
    • low Risky intent intent-offensive-security references/implementation-and-infrastructure.md:105
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Resilience testing program covers all 12 required test types** -- with annual penetration testing, scenario-based exercises, and TLPT preparation (if applicable) per Articles 24-27
    • low Risky intent intent-offensive-security SKILL.md:25
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Resilience testing program design** — basic testing (12 test types) plus advanced Threat-Led Penetration Testing (TLPT) per the TIBER-EU framework
    • low Risky intent intent-offensive-security SKILL.md:80
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - Actual penetration testing execution or vulnerability scanning -- this skill provides planning and assessment frameworks, not testing tools

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 61/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 40Result and completion. Does not say what the result is
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 32 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1850 tokens
    • 100Running it twice. No mutating operations

    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 222: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 32 items
    • +4Has examples (1 code blocks)
    • +4Reference files are cited in the instructions (6 of 6)
    • +3All 2 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.