Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
.claude/skills/borghei-dora-compliance-expert/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 143% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -23% | 0% |
Tools and guidance for Regulation (EU) 2022/2554 on digital operational resilience for the financial sector (Digital Operational Resilience Act — DORA). DORA is a directly applicable EU regulation (applicable since January 17, 2025) covering 20 types of financial entities and their critical ICT third-party providers. This skill assesses readiness against the five pillars, classifies ICT incidents and computes reporting deadlines, and structures third-party risk and resilience-testing programs.
Before running the assessment, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the assessment.
bash# Generate and run a 5-pillar readiness assessment python scripts/dora_readiness_checker.py --template > assessment.json python scripts/dora_readiness_checker.py --config assessment.json --json # Classify an ICT incident and get reporting deadlines python scripts/dora_incident_classifier.py --clients-affected 5000 --duration-hours 4 \ --data-loss yes --services-critical yes --economic-impact 500000
Load the reference that matches the task — keep this file lean and pull detail on demand:
In Scope:
Out of Scope:
infrastructure-compliance-auditor for technical security controlsImportant Notes:
| Skill | Integration | When to Use | |-------|-------------|-------------| | information-security-manager-iso27001 | ISO 27001 controls map directly to DORA Pillar 1 requirements; ISO 27001 certification supports DORA compliance evidence | When building ICT risk management framework aligned with both ISO 27001 and DORA | | nis2-directive-specialist | DORA is lex specialis for financial sector; NIS2 applies residually; coordinate incident reporting timelines | When financial entity also falls under NIS2 scope for non-financial ICT services | | infrastructure-compliance-auditor | Technical infrastructure checks validate DORA Pillar 1 (protection, detection) and Pillar 3 (resilience testing) controls | When assessing actual infrastructure security posture against DORA requirements | | nist-csf-specialist | NIST CSF 2.0 functions map to DORA pillars; useful for organizations with US operations | When building a unified resilience framework across US and EU requirements |
Last Updated: June 2026 Regulation Reference: EU 2022/2554 Applicable From: January 17, 2025
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,019 | 16,821 | -7% | 1 | 1 | 0% | 3,131 | 4,528 | +45% | 0 | 0 | — |
case-02 | pass→pass | 39,182 | 23,716 | -39% | 1 | 1 | 0% | 6,220 | 5,810 | -7% | 0 | 0 | — |
case-03 | fail→pass | 9,070 | 5,161 | -43% | 1 | 1 | 0% | 1,480 | 2,623 | +77% | 0 | 0 | — |
case-04 | pass→pass | 6,833 | 9,977 | +46% | 1 | 1 | 0% | 1,266 | 3,342 | +164% | 0 | 0 | — |
case-05 | pass→pass | 6,576 | 7,594 | +15% | 1 | 1 | 0% | 1,105 | 2,892 | +162% | 0 | 0 | — |
case-06 | fail→pass | 6,172 | 5,532 | -10% | 1 | 1 | 0% | 1,065 | 2,590 | +143% | 0 | 0 | — |
case-07 | fail→pass | 9,184 | 1,939 | -79% | 1 | 1 | 0% | 1,334 | 1,957 | +47% | 0 | 0 | — |
case-08 | pass→pass | 10,069 | 7,111 | -29% | 1 | 1 | 0% | 1,703 | 3,051 | +79% | 0 | 0 | — |
case-09 | fail→pass | 13,136 | 8,521 | -35% | 1 | 1 | 0% | 2,171 | 2,950 | +36% | 0 | 0 | — |
case-10 | pass→pass | 8,464 | 8,224 | -3% | 1 | 1 | 0% | 1,306 | 2,921 | +124% | 0 | 0 | — |
case-11 | pass→pass | 5,810 | 5,517 | -5% | 1 | 1 | 0% | 958 | 2,479 | +159% | 0 | 0 | — |
case-12 | pass→pass | 7,134 | 4,100 | -43% | 1 | 1 | 0% | 1,318 | 2,406 | +83% | 0 | 0 | — |
case-13 | fail→pass | 17,170 | 3,432 | -80% | 1 | 1 | 0% | 2,873 | 2,200 | -23% | 0 | 0 | — |
case-14 | fail→pass | 10,069 | 2,129 | -79% | 1 | 1 | 0% | 1,721 | 2,001 | +16% | 0 | 0 | — |
case-15 | fail→pass | 2,823 | 14,870 | +427% | 1 | 1 | 0% | 309 | 4,178 | +1252% | 0 | 0 | — |
case-16 | pass→pass | 3,062 | 2,394 | -22% | 1 | 1 | 0% | 514 | 2,001 | +289% | 0 | 0 | — |
case-17 | pass→pass | 4,360 | 3,851 | -12% | 1 | 1 | 0% | 661 | 2,279 | +245% | 0 | 0 | — |
case-18 | pass→pass | 13,179 | 12,021 | -9% | 1 | 1 | 0% | 2,140 | 3,591 | +68% | 0 | 0 | — |
case-19 | fail→pass | 4,961 | 1,561 | -69% | 1 | 1 | 0% | 703 | 1,880 | +167% | 0 | 0 | — |
case-20 | pass→pass | 7,487 | 9,642 | +29% | 1 | 1 | 0% | 647 | 2,691 | +316% | 0 | 0 | — |
case-21 | pass→pass | 9,584 | 4,264 | -56% | 1 | 1 | 0% | 1,571 | 2,321 | +48% | 0 | 0 | — |
case-22 | pass→pass | 16,737 | 14,080 | -16% | 1 | 1 | 0% | 2,639 | 4,003 | +52% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.