Jsp 912 logo

Jsp 912

Community
jgsystemsconsulting
jsp-912

Knowledge pack synthesized from JSP 912 Human Factors Integration in Defence Systems, Part 1 Directive and Part 2 Guidance, V3.0 (March 2024, Ministry of Defence, Open Government Licence v3.0): Human Factors Integration in Defence acquisition. SCOPE LIMITS: both parts in one pack; MOD policy, not statute; not Defence SMS (use jsp-815) and not acquisition-safety policy (use jsp-376); not dependable-AI direction (use jsp-936); JSP 375, JSP 536, JSP 815, JSP 822, and DEF-STANs named, not quoted; reconstructed reference notes, not MOD guidance, and no official status.

Overview

Publisherjgsystemsconsulting
Repositoryjgs-se-knowledge-packs
Skill namejsp-912
Stars
121
Forks
1
Bundled files
12
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jgsystemsconsulting on GitHub. Read the source before you install it.

Installation

Install the Jsp 912 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/jsp-912
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs.git /tmp/jgs-se-knowledge-packs
mkdir -p .claude/skills
cp -r /tmp/jgs-se-knowledge-packs/packs/jsp-912 .claude/skills/jsp-912
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jsp 912 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Jsp 912 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Jsp 912 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

JSP 912: Human Factors Integration in Defence Systems (Parts 1 and 2)

When to use

Prerequisites: none required; plain Markdown. Familiarity with defence acquisition lifecycles (CADMID, business cases) helps; glossary.md defines MOD-specific terms.

Use this skill for questions about how UK Defence mandates and runs Human Factors Integration: what HFI is and how it differs from Human Factors Engineering, how it sits inside systems engineering and the Defence Lines of Development, the six HFI process stages (HFI-1.0 through HFI-6.0), tailoring, and the six MOD staff roles that carry it. It is a policy-and-process pack; it does not cover the Defence safety management system (use jsp-815), acquisition safety policy (use jsp-376), or dependable-AI direction (use jsp-936).

Source: Contains public sector information licensed under the Open Government Licence v3.0. JSP 912 Human Factors Integration in Defence Systems, Part 1 Directive and Part 2 Guidance, V3.0 (March 2024), Ministry of Defence, Crown copyright. Reconstructed reference notes, not reproductions; licence text and source link in LICENSE.

How to Use This Skill

  • Without arguments: read Core Frameworks & Mental Models below.
  • With a topic: use the Topic Index and follow the arrow to a chapter.
  • With a role or stage-gate question: use the Chapter Index and read the matching chapter.
  • For a term use glossary.md; for a stage gate or role use cheatsheet.md.

Core Frameworks & Mental Models

What HFI is (Part 1, echoed in Part 2)

HFI is a management activity: a systematic process for identifying, tracking and resolving people-related considerations so the technological and human aspects of capability develop in balance. Human Factors is the science, Human Factors Engineering is its design application, and HFI is the management process over both, organised through five domains: Personnel, Training, Human Factors Engineering, System Safety & Health Hazards, and Organisational & Social. MOD policy applies HFI to every defence acquisition activity, Development Item, Non-Development Item, Off-The-Shelf, demonstrators and upgrades alike, with scope set by risk, not exemption.

Six stage gates across the lifecycle (Part 2)

The process runs in six top-level stages: HFI-1.0 User Need Definition and HFI-2.0 System Requirements Definition before contract, HFI-3.0 Assess Tenders at selection, HFI-4.0 Detailed System Design under contract, HFI-5.0 Test and Acceptance per the ITEA Plan, and HFI-6.0 In-Service Feedback through life. Seven goals govern every activity, from RAIDO management from the outset to formal acceptance of people-related aspects.

Tailoring keeps it proportionate (Parts 1 and 2)

Tailoring is the process of setting the range and depth of HFI activities against scope, size, complexity, lifecycle phase and contractual arrangements. It starts internally before Outline Business Case, informed by the Early Human Factors Analysis, is re-tested at tender preparation, and is revisited jointly after contract award, with MOD holding the final decision and the HFI Policy team agreeing every tailoring. Detail is tailorable; whole stages are not.

Six roles carry the work (Parts 1 and 2)

Project Team Leader holds prime responsibility; the HFI Focus splits into HFIF(Cap) before contract and HFIF(PT) inside the project team; the Requirements Manager translates user requirements into system requirements; the Capability Sponsor owns the programme level; the CIWG integrates across DLODs; and the HFI Support Function (the DE&S HFI Policy team) agrees tailoring and assures application. Everyone undertaking HFI is SQEP, with human-participant research governed by JSP 536, which is named here but not reproduced.

Chapter Index

ChChapterSourcesCoverage
01ch01-what-is-hfi-and-why-defence-mandates-it.mdPart 1 pp. 1-4 + Part 2 pp. 1-6What HFI is, HF vs HFE, the five HFI domains, the mandate, the Human Component of Capability.
02ch02-roles-and-responsibilities.mdPart 1 pp. 7-8 + Part 2 pp. 45-47The six MOD staff roles, the two HFI Focus posts, requirements management and the Golden Thread.
03ch03-hfi-and-systems-engineering.mdPart 2 pp. 4-6, 10-12HFI inside systems engineering, DLOD considerations, System Readiness Levels with HFI as a driver.
04ch04-hfi-process-goals-activities-tailoring.mdPart 1 pp. 5-6 + Part 2 pp. 7-9, 41-44Seven process goals, six stage overview, tailoring regime, project types (DI, NDI, OTS).
05ch05-user-need-and-system-requirements.mdPart 2 pp. 13-22HFI-1.0 User Need Definition and HFI-2.0 System Requirements Definition: EHFA, RAIDO register, HFUR/HFSR/HFPR.
06ch06-assess-tenders-hfi-3-0.mdPart 2 pp. 23-24HFI-3.0 Assess Tenders: tenderer's HFI Plan, five assessment criteria, independent design analysis.
07ch07-detailed-system-design-hfi-4-0.mdPart 2 pp. 25-33HFI-4.0 Detailed System Design: HFI Working Group, joint RAIDO management, conduct of activities, deliverables.
08ch08-test-acceptance-in-service-feedback.mdPart 2 pp. 34-40HFI-5.0 Test and Acceptance and HFI-6.0 In-Service Feedback: ITEA, VVRM, design freeze, lessons through life.
09ch09-competencies-ethics-conduct.mdPart 1 p. 9 + Part 2 pp. 48-49SQEP requirements, Awareness and Practitioner levels, CIEHF membership, JSP 536 research ethics, codes of conduct.

Topic Index

  • Human Factors Integration (HFI): definition and mandate → ch01
  • Human component of capability and integration duties → ch01
  • HFI domains (Personnel, Training, HFE, System Safety & Health Hazards, Organisational & Social) → ch01
  • Human Factors Engineering and domain coupling → ch01, ch03
  • Systems engineering alignment and ISO/IEC 15288 → ch03
  • Defence Lines of Development (DLOD) considerations → ch03
  • System Readiness Levels (SRL) and HFI maturity → ch03
  • Stage gate HFI-1.0 User Need Definition → ch05
  • Stage gate HFI-2.0 System Requirements Definition → ch05
  • Stage gate HFI-3.0 Assess Tenders → ch06
  • Stage gate HFI-4.0 Detailed System Design → ch07
  • Stage gate HFI-5.0 Test and Acceptance → ch08
  • Stage gate HFI-6.0 In-Service Feedback → ch08
  • HFI goals and process activities → ch04
  • Tailoring and project types (DI, NDI, OTS/MOTS) → ch04
  • Roles: Project Team Leader, HFI Focus, Requirements Manager, Capability Sponsor, CIWG, HFI Support Function → ch02
  • HFI RAIDO Register and requirements types (HFUR, HFSR, HFPR) → ch05, ch07
  • HFI Working Group and HFI Steering Group → ch05, ch07
  • Competencies, SQEP and CIEHF membership → ch09
  • Research ethics and conduct (JSP 536, BPS, CIEHF codes) → ch09
  • Test evidence, ITEA Plan and VVRM → ch08
  • In-service lessons and Learning from Experience → ch03, ch08
  • Policy interfaces to JSP 375, JSP 536, JSP 815, JSP 822 and Def Stan 00-251 → ch01, ch09

Supporting Files

  • glossary.md: terms and acronyms the source defines or characterises, alphabetical, with the chapters that use each.
  • cheatsheet.md: the six stage gates (HFI-1.0 through HFI-6.0) and six roles in prose.

Scope & Limits

  • Source version: JSP 912 Human Factors Integration in Defence Systems, Part 1 Directive and Part 2 Guidance, V3.0 (March 2024); vetted 2026-10-28 against the publication page and both PDFs (Part 1 16 pages, Part 2 65 pages).
  • Coverage: HFI in UK Defence acquisition only. This pack is process and policy, not a technical handbook, and contains no figures or page images from the source.
  • Not the Defence SMS: safety management system obligations live in JSP 815; use the jsp-815 pack. Not reproduced here.
  • Not acquisition-safety policy: use jsp-376 for that. Not reproduced here.
  • Not dependable-AI direction: use jsp-936 for that. Not reproduced here.
  • Other publications named, not quoted: JSP 375, JSP 536, JSP 815, JSP 822, Def Stan 00-251, Def Stan 23-009, Def Stan 00-600, ISO/IEC 15288 and other standards are named for navigation only; consult each directly for its requirements.
  • Not official MOD guidance: reconstructed reference notes with no official status and no MOD endorsement. Source identification and licence only in LICENSE.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Jsp 912 AI skill do?

Knowledge pack synthesized from JSP 912 Human Factors Integration in Defence Systems, Part 1 Directive and Part 2 Guidance, V3.0 (March 2024, Ministry of Defence, Open Government Licence v3.0): Human Factors Integration in Defence acquisition. SCOPE LIMITS: both parts in one pack; MOD policy, not statute; not Defence SMS (use jsp-815) and not acquisition-safety policy (use jsp-376); not dependable-AI direction (use jsp-936); JSP 375, JSP 536, JSP 815, JSP 822, and DEF-STANs named, not quoted; reconstructed reference notes, not MOD guidance, and no official status.

Why use Jsp 912 on TypingMind?

Because you install it once and use it with any model. Jsp 912 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Jsp 912 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/jsp-912. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Jsp 912?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Jsp 912?

As many as you like. As long as a model supports skills, you can use Jsp 912 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Jsp 912 AI skill free?

It is published on GitHub by jgsystemsconsulting. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇