SKILLEMALL.ai
GitHub ↗ RU Sign in

BC jsp-936

Knowledge pack synthesized from JSP 936 Dependable Artificial Intelligence (AI) in Defence, Part 1: Directive, V1.1 (November 2024, Ministry of Defence, Open Government Licence v3.0): dependable-AI direction for Defence. SCOPE LIMITS: single-source (JSP 936 Part 1 V1.1); MOD policy, not statute; not the Defence SMS (use jsp-815) and not acquisition-safety policy (use jsp-376); Part 2 is not in this pack; no DEF-STAN text and no other JSP reproduced; reconstructed reference notes, not MOD guidance, and no official status.

jgsystemsconsulting/jgs-se-knowledge-packs Agent Skills author: jgsystemsconsulting 13 files body ≈ 2 037 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Knowledge pack synthesized from JSP 936 Dependable Artificial Intelligence (AI) in Defence, Part 1: Directive, V1.1 (November 2024, Ministry of Defence, Open…

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureInfrastructureSecuritytype 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
B
91/100
safety, quality, tests
Safety 60%
98
Quality 40%
81
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security chapters/ch01-introduction.md:31
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      - In-scope examples named in the directive include object detection in ISR, reinforcement learning in command and control and autonomous systems, LLMs in HR applications, and AI in decision-support to
      detector
    • low Risky intent intent-offensive-security glossary.md:13
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **C2 (Command and Control)**: application area named among in-scope examples, including reinforcement learning used in C2 and autonomous systems. → ch01, ch02

    Files scanned: 13. 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 58/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 3 mutating operations with no state check
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 37 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2037 tokens

    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
    • +4No input/output examples
    • +2Single-language instructions
    • +3Description length 526: enough signal without eating the budget
    • +4Structure: 12 headings
    • +3Step-by-step instructions: 37 items
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.