BB nzism
Expert New Zealand Information Security Manual (NZISM) advisor for NZ government agencies and their supply chains. Use for NZISM control guidance, gap analysis, agency security obligations, classification framework (Unclassified through Top Secret), security risk management, system certification, and GCSB/NCSC NZ compliance. Triggers on: NZISM controls, NZ government security, GCSB compliance, agency cybersecurity obligations, NZ classification markings, Restricted/Confidential/Secret system scoping, agency security policies, third-party supplier security, Certification and Accreditation (C&A), and any question about NZ government information security requirements or the NZISM framework.
Expert New Zealand Information Security Manual (NZISM) advisor for NZ government agencies and their supply chains.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, consistency
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securityreferences/control-groups.md:181Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration testing — before major releases and at least annually for internet-facing systems
-
low Risky intent
intent-offensive-securitySKILL.md:143Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Independent assurance evidence**: current ISO/IEC 27001 certificate (scope checked), **SOC 2 Type II report**, **IRAP assessment** or equivalent government-grade assessment, recent independent **p
Files scanned: 6. 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 68/100
- 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 (nzism) differs from the folder (nzism-tanaji-hemant-naik)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 3653 tokens
- 100Progress reporting. Reports progress
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)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 696: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 57 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.