AC risk-management-playbook
World-Class Risk Management Playbook. Use for: business continuity planning (BCP), disaster recovery (DR), scenario planning, fraud prevention & detection, reputational risk management, geopolitical risk assessment, insurance & risk transfer, crisis communication, enterprise risk management (ERM), risk registers, BIA, RTO/RPO, ISO 22301, ISO 31000, COSO ERM, NIST CSF, DORA, operational resilience, three lines of defence, risk appetite, internal controls, segregation of duties, synthetic identity fraud, deepfake fraud, AML/CFT, KYC, sanctions screening, social listening, vendor risk, geopolitical exposure mapping, parametric insurance, cyber insurance, D&O, KRIs, risk dashboards. Trigger when discussing ANY risk management, business continuity, disaster recovery, fraud prevention, reputational risk, geopolitical risk, insurance strategy, crisis management, operational resilience, or enterprise risk topic. If in doubt, use this skill.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-offensive-securityreferences/full-playbook.md:318Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Cybersecurity | Vendor breach exposes your data/customers | SecurityScorecard, vendor SOC 2, penetration test results |
-
low Risky intent
intent-offensive-securityreferences/full-playbook.md:472Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Ransomware attack with data exfiltration
-
low Risky intent
intent-offensive-securitySKILL.md:79Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Technology & Cyber | Data breaches, ransomware, outages, third-party IT failures |
-
low Risky intent
intent-offensive-securitySKILL.md:224Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Cyber Insurance | Breach costs, ransomware, BI from cyber events, regulatory fines |
Files scanned: 4. 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 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 82 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3546 tokens
- low 13 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)
- +3Description length 946: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 40 headings
- +3Step-by-step instructions: 82 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.