CC dora
Expert DORA (Regulation (EU) 2022/2554 — Digital Operational Resilience Act) compliance advisor for EU financial entities. Use this skill whenever a user asks about DORA compliance, ICT risk management frameworks, ICT incident classification or reporting, threat-led penetration testing (TLPT), ICT third-party risk management, Register of Information, contractual provisions with ICT providers, ICT concentration risk, oversight of critical ICT third-party service providers (CTPPs), or any DORA RTS/ITS obligation. Also trigger for: "DORA gap analysis", "DORA readiness", "Art. 6 ICT risk framework", "Art. 17 incident reporting", "Art. 26 TLPT", "Art. 28 third-party policy", "Art. 30 contractual provisions", "Register of Information CIR 2024/2956", "critical TPSP designation", "DORA vs NIS2", "DORA simplified framework", or EBA/ESMA/EIOPA digital resilience guidance.
Expert DORA (Regulation (EU) 2022/2554 — Digital Operational Resilience Act) compliance advisor for EU financial entities.
As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Risky intent
intent-offensive-securityREADME.md:114Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)"We experienced a ransomware incident that encrypted our trading system
quoted -
low Risky intent
intent-offensive-securityREADME.md:207Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)`DORA`, `Digital Operational Resilience Act`, `Regulation (EU) 2022/2554`, `DORA compliance`, `DORA gap analysis`, `ICT risk management framework`, `ICT RMF DORA`, `Art. 6 DORA`, `Art. 17 DORA`, `Art.
quoted -
low Risky intent
intent-offensive-securityreferences/rts-its-guide.md:180Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Requirements for **red team testing**: methodology, documentation, attestation
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "Expert DORA (Regulation (EU) 2022/2554 — Digital Operational Resilience Act) compliance advisor for EU financial entities. Use this skill whenever a user asks about DORA compliance, ICT
quoted -
low Risky intent
intent-offensive-securitySKILL.md:275Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Threat-Led Penetration Testing (TLPT)** is required for significant financial
-
low Risky intent
intent-offensive-securitySKILL.md:456Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## TLPT — Threat-Led Penetration Testing
-
low Risky intent
intent-offensive-securitySKILL.md:471Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **Red team test** — External red team performs adversarial simulation
-
low Risky intent
intent-offensive-securitySKILL.md:490Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)| Calling TLPT a "penetration test" | TLPT is intelligence-led adversarial simulation, not a standard penetration test |
table
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6276 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 23, 250, 425): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (dora) differs from the folder (dora-tanaji-hemant-naik)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6276 tokens
- 85Steps. 139 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 874: 120–800 characters recommended
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 51 headings
- +3Step-by-step instructions: 139 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.