Se logo

Se

Community
jgsystemsconsulting
se

Orchestrator (not a knowledge pack): routes a free-text systems-engineering question to the right catalogue pack(s), reads them with you, and answers with pack and chapter citations. Runs only on explicit `/se <question>`; carries no source content. Use when you do not know which `/pack` to ask.

Overview

Publisherjgsystemsconsulting
Repositoryjgs-se-knowledge-packs
Skill namese
Stars
121
Forks
1
Bundled files
1
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.

  • 1 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 Se 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/se
  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/se .claude/skills/se
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Se 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 Se 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 Se 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.

SE Orchestrator: routes questions to the right knowledge packs

This is an orchestrator, not a knowledge pack. It carries no source content. On explicit /se <question> it matches your question to installed catalogue packs, reads them, and answers with pack and chapter citations.

When to use

Prerequisites: none: plain Markdown; works on any host that loads Agent Skills. Pair it with the packs it routes to.

/se answers systems-engineering questions by consulting installed packs. It is an entry point, not a knowledge base. Use it when you do not already know which /<slug> to open.

How /se answers

Modes

ModeWhenGate
Narrow consultOne Topics row matches, at most one agency named, no compare/contrast/survey verbNone. Best single pack. End with "Also relevant" runners-up.
Broad consultTwo or more Topics rows, two or more agencies, or a compare/contrast/survey verbOne plan approval naming packs and why, then run to done. Disagreements under "Where the sources differ"; never average or blend.
DeliverableAn artifact verb (draft, write, produce, prepare, build, review, verify) plus a Deliverables row name or keywordPlan approval, then stage pauses after Draft and after Review (Verify is last).

Routing

  1. Match Topics keywords case-insensitively, with synonym judgement (e.g. "V&V" hits verification and validation rows).
  2. Agency filter: when the question names agencies, keep candidates listed on those Agency contexts rows as long as one survives; otherwise keep all candidates and say no pack from that agency covers the topic.
  3. Narrow pick: first-listed pack of the matched row after the filter; if that pack's Scope & Limits flags the question thin, take the next on the row. The consult stays narrow (no gate).
  4. Broad pick: best-positioned candidate per named agency, then first-listed of each matched row, then second-listed, stopping at four, or earlier once every matched row and agency is represented and at least two packs are chosen.
  5. No match: name the three closest Topics rows, suggest a rephrase or a direct /<slug>, and make no SE claims.

Reading

A pack lives at ../<slug>/ from this folder (native installs put members side by side). For each selected pack: read its SKILL.md index; open at most two chapters from its Topic Index / Chapter Index; open one support file (glossary.md, patterns.md, or cheatsheet.md) only for term, technique, or decision-rule questions. At most four packs total. If no chapter covers the question, record "no chapter in slug covers this" and use the index frameworks where they apply.

Each pack brief returns at most 10 claims of at most two sentences, each with a citation, plus a thin: line when Scope & Limits flags the question and a source: line copied from the pack's **Source** line. No claim from outside its pack.

Citations and Sources

Cite only files read this session, in these forms: [slug chNN], [slug index], [slug glossary|patterns|cheatsheet]. Drop uncited claims. Agreeing claims merge into one statement carrying every citation. Where the packs are silent, say so; no fallback to model memory. Every answer ends with a Sources block listing each pack's slug, its **Source** line, and its licence. Content-pack licences come from the Licences table, else the label Public Domain (US Government work). Signpost lines read MIT (signpost). Non-commercial and share-alike terms appear in full.

Deliverable stage chains

The matched Deliverables row is the chain. Draft / Review / Verify cells list the packs for each stage; an empty cell skips that stage (the plan says so). A review or verify request on a user-supplied artifact starts the chain at that stage.

  • Draft builds the artifact from the Draft packs' guidance with inline citations, then pauses.
  • Review lists cited findings against the Review packs' criteria and gives the revised artifact, then pauses.
  • Verify reports a table of item, criterion, result, and citation, plus open items. It edits nothing and offers fixes as a follow-up.

Output goes in the reply unless the user names a file. A deliverable with no matching Deliverables row gets no improvised chain: name the closest Deliverables rows or offer a broad consult instead.

Edge cases

  • Bare /se with no argument: print usage and three example questions (e.g. requirements quality, NASA risk process, hazard analysis draft).
  • Sub-agent failure: rerun that brief in the main thread.
  • Thin-pack step-down: if the selected pack's Scope & Limits flags the question thin, take the next pack on the row; the consult stays narrow.

Routing map

Topics

TopicKeywordsPacks (best first)
SE fundamentals & systems thinkingsystems engineering, lifecycle, systems thinking, SE process, what is SEsebok, nasa-se-handbook, dau-se-guidebook, nist-cps
Requirements engineeringrequirements, shall statements, EARS, requirement quality, weak words, verifiable requirementsrequirements-writing, faa-req-handbook, nasa-se-handbook
Requirements traceability & allocationtraceability, allocation, flow-down, bidirectional traceabilityfaa-req-handbook, requirements-writing, faa-std-025
Architecture & designarchitecture, architecture framework, design solution, MOSA, modular open systemsdodaf, dod-mosa, nasa-se-handbook, sebok
Interface managementinterfaces, ICD, interface control, ICID, interface definitionis-gps-200n, faa-std-025, nasa-se-handbook, faa-sem
Integrationintegration, assembly, integration readiness, integration planningnasa-se-handbook, nasa-se-expanded, doe-sem, dafman-63-119
Verificationverification, verification methods, test/analysis/inspection/demonstration, verifiabilityfaa-ams-vv, dod-vva-rpg, nasa-se-handbook, dote-te-guidebook
Validationvalidation, effectiveness, operational suitability, user needsdod-vva-rpg, faa-ams-vv, nasa-se-handbook, dote-te-guidebook
Test & evaluationtest and evaluation, T&E, developmental test, operational test, test readinessdod-te-guidebook, dote-te-guidebook, dafman-63-119, dod-vva-rpg
Modeling, MBSE & simulationMBSE, SysML, modelling, simulation credibility, M&Snasa-systems-modeling, nasa-ms-7009, dod-vva-rpg, dodaf
Digital engineeringdigital engineering, digital twin, digital thread, model-centric acquisitiondod-digital-engineering, digital-systems-engineering, nasa-de-acquisition
Configuration managementconfiguration management, baselines, change control, CM plansmil-hdbk-61, nasa-se-handbook, faa-std-025
Data & information managementdata management, technical data, data rights, information modelsmil-hdbk-61, dodaf, nasa-de-acquisition, nasa-npr-7150, nist-cps
Risk managementrisk, risk register, risk matrix, likelihood, consequence, risk acceptance, continuous risk managementnasa-risk, dod-rio, nist-ai-rmf
Opportunity & benefit managementopportunity, benefit, benefit-cost analysis, cost-effectiveness, BCAfederal-bca, dod-rio
Trade studies & decision analysistrade study, decision analysis, alternatives, selection criteria, weightingnasa-se-handbook, federal-bca, nasa-ceh, dod-vva-rpg
Work breakdown & technical planningWBS, work breakdown structure, technical plans, SOW, planning packagesmil-std-881f, nasa-se-handbook, nasa-npr-7123, doe-sem
Technical measurement & assessmentTPM, technical performance measures, TRL, MRL, readiness assessment, statistical methodsgao-tra, mrl-deskbook, nist-stat-handbook, nasa-ms-7009
Quality assurance & airworthinessQA, quality assurance, process compliance, airworthiness certificationmil-hdbk-516, gao-agile, nist-stat-handbook
System safety & hazardssafety, system safety, hazard analysis, fault management, PRA, mishapmil-std-882, nasa-system-safety, faa-system-safety, nasa-pra, nasa-fault-management
Reliability & maintainabilityreliability, maintainability, availability, RMA, R&M, failure ratesmil-hdbk-338, faa-rma, nasa-rm-standard
Cybersecurity & security engineeringcybersecurity, security engineering, RMF, incident response, CUI, secure software, CSFnist-csf, nist-sse, nist-800-37, nist-800-171, nist-800-61, nist-ssdf
Cyber performance goals & infrastructurecritical infrastructure, performance goals, sector security, CPScisa-cpg, nist-csf, nist-cps
Human factors & HSIhuman factors, HSI, usability, workload, crew stations, anthropometryfaa-hf-std, nasa-hsi, mil-hdbk-516
Logistics, sustainment & obsolescencelogistics, sustainment, supportability, DMSMS, obsolescence, parts managementsd-22-dmsms, dote-te-guidebook
Orbital debris & end-of-life disposalorbital debris, passivation, reentry, disposal, spacecraft end-of-lifenasa-std-8719-14, nasa-se-handbook
Technical documentation & manualstechnical manuals, documentation standards, page-based documentationmil-std-40051, faa-std-025
Cost & schedulecost estimating, schedule, EVM, budget, program cost, schedule margingao-cost, gao-schedule, nasa-schedule, nasa-ceh, gao-agile
Manufacturing & quality engineeringmanufacturing readiness, MRL, production, quality engineering, factorymrl-deskbook, dod-mq-bok
Agile in government programsagile, incremental delivery, iterative development, scrum oversightgao-agile
Acquisition & suppliersacquisition, procurement, supplier, contract, sourced approvaldoe-o-413-3, nasa-de-acquisition, dod-mosa, mrl-deskbook, nasa-npr-7123
Governance, reviews & gatesreviews, gates, KDPs, milestones, certification, test readiness certificationdafman-63-119, eu-ai-act, doe-o-413-3, nasa-npr-7123, dau-se-guidebook
SE standards & process modelsSE standards, ISO 15288, tailoring, lifecycle models, NPR requirementssebok, nasa-npr-7150, nasa-npr-7123, dau-se-guidebook, nasa-se-handbook
AI & cyber-physical systemsAI, AI risk management, autonomous systems, cyber-physical, CPS, EU AI Actnist-ai-rmf, nist-cps, eu-ai-act, jsp-936
Modelling language specificationsSysML spec, UML, UAF, BPMN, OMG specificationsomg-signpost, nasa-systems-modeling
SE standards landscape lookupISO/IEC/IEEE standards, INCOSE handbook, ECSS, SAE, where to get a standardse-standards-signpost, sebok
Vehicle safety & automotivevehicle safety, automotive, FMVSS, ADS, automated driving, vehicle cybersecuritynhtsa-vehicle, automotive-signpost, functional-safety-signpost
Civil infrastructure & ITSintelligent transportation, ITS, systems engineering analysis, 23 CFR 940, ConOpsfhwa-its-se
GPS & GNSS interfacesGPS, GNSS, NAVSTAR, space segment interface, ranging signalis-gps-200n, faa-std-025
Medical device softwareFDA, QMSR, 510(k), device software, SaMD, eSTAR, MDR, IVDR, MHRA, UKCA, MDCGfda-med-device, med-device-eu
Avionics software assuranceDO-178C, DO-254, 8110.49, airborne software, AEH, conformityfaa-8110-49, avionics-signpost, easa-rules
Railway RAMS & signalling assuranceEN 50126, EN 50128, EN 50129, railway RAMS, CSM, signalling assurance, RSSBrail-signpost
Space standards (ECSS)ECSS, space standards, E-ST-10, E-ST-40, Q-ST-30, space environment, product assurancespace-signpost
Maritime safety and class rulesSOLAS, ISM, ISPS, COLREGS, USCG, class rules, MCAmaritime-signpost
Defence safety managementJSP 815, JSP 376, JSP 912, acquisition safety, defence safety, SMS, safety case, assurance, dependable AI, AI assurance, human factors, HFI, human componentjsp-815, jsp-376, jsp-936, jsp-912
Nuclear software assuranceNRC, regulatory guide, NUREG, digital safety systems, software assurance, BTP 7-14nrc-nuclear

Agency contexts

AgencyKeywordsPacks
NASANASA, NPR, NASA-STD, NASA-HDBK, missionnasa-se-handbook, nasa-npr-7123, nasa-npr-7150, nasa-risk, nasa-system-safety, nasa-hsi
DoD / DAU / OSDDoD, MIL-STD, MIL-HDBK, DAU, OSD, DOT&E, DAF, SD-22, MRLdau-se-guidebook, dod-rio, mil-std-882, dod-te-guidebook, mil-hdbk-61, dodaf
NISTNIST, SP 800, framework, FIPSnist-csf, nist-sse, nist-800-37, nist-800-171, nist-ai-rmf, nist-stat-handbook
FAAFAA, AMS, air traffic, civil aviationfaa-sem, faa-ams-vv, faa-req-handbook, faa-system-safety, faa-hf-std, faa-rma
GAOGAO, schedule assessment, cost assessment, agile assessment, TRAgao-cost, gao-schedule, gao-tra, gao-agile
DOEDOE, department of energy, order 413doe-sem, doe-o-413-3
CISA / DHSCISA, DHS, critical infrastructure, performance goalscisa-cpg
OMBOMB, circular A-94, federal benefit-costfederal-bca
EUEU, European Union, AI Act, regulationeu-ai-act
NHTSA / USDOTNHTSA, USDOT, FMVSS, vehicle safety standard, automated driving systemsnhtsa-vehicle
FHWA / USDOT ITSFHWA, ITS, systems engineering analysisfhwa-its-se
FDAFDA, CDRH, QMSR, 21 CFR 820, 510(k)fda-med-device
NRCNRC, regulatory guide, NUREG, BTP 7-14nrc-nuclear
EASAEASA, AMC 20-115D, AMC 20-152A, Easy Access Ruleseasa-rules
EU / MHRAMDCG, MDR, IVDR, MHRA, UKCA, SaMDmed-device-eu

Deliverables

DeliverableKeywordsDraftReviewVerify
Requirements specificationrequirements doc, SRD, shall statements, spec treerequirements-writing, faa-req-handbookrequirements-writingfaa-ams-vv
ConOpsconcept of operations, ConOps, operational concept, scenariosnasa-se-handbook, seboknasa-se-handbookfaa-ams-vv
Risk registerrisk register, risk log, risk statement, mitigation plannasa-risk, dod-rionasa-riskdod-rio
Verification planverification plan, V&V plan, verification matrixfaa-ams-vv, dod-te-guidebookfaa-ams-vvdote-te-guidebook
Hazard analysishazard analysis, hazard log, safety assessment, FMEAmil-std-882, nasa-system-safetymil-std-882faa-system-safety
Interface control documentICD, interface control document, interface definitionfaa-std-025, is-gps-200nfaa-std-025
Trade studytrade study, trade-off analysis, alternatives evaluationnasa-se-handbook, federal-bcanasa-se-handbook
Work breakdown structureWBS, work breakdown structure, WBS dictionarymil-std-881f, nasa-se-handbookmil-std-881f

Licences

PackLicence
sebokCC BY-NC-SA 3.0
requirements-writingOriginal guidance (CC BY 4.0); cited methods not reproduced
digital-systems-engineeringCC BY 4.0
eu-ai-actEU Official Journal — reproduction authorised with source acknowledgement (Decision 2011/833/EU)
jsp-815Open Government Licence v3.0
jsp-376Open Government Licence v3.0
jsp-936Open Government Licence v3.0
jsp-912Open Government Licence v3.0
easa-rulesPer-document: EASA site reproduction-with-acknowledgement grant, qualified by ED Decision all-rights-reserved footers; reconstructed notes with attribution; official PDFs not redistributed; commercial use pending per-document determination
med-device-euPer-document: European Commission reuse policy (Decision 2011/833/EU, CC BY 4.0, attribution and indication of changes) for the MDCG documents; Open Government Licence v3.0 for the MHRA guidance; reconstructed notes with attribution; official PDFs not redistributed

Host modes

Pick the highest mode the host can run:

ModeWhenBehaviour
Fan-outSub-agents availableOne brief per pack in parallel; main thread composes the answer. On sub-agent failure, rerun that brief in the main thread.
SequentialNo sub-agents, member files readableSame briefs one at a time; write each pack's notes before opening the next.
Index-onlyTransform installs (Codex, Gemini, Cursor rules)Read sibling index files when readable. Cite [slug index] only, name chapters as follow-ups, and label the answer index-level: chapter bodies not installed.
Route-onlyNo member file readableReport the routing decision and the /slug commands only. Make no SE claims.

Native-root fallback. When the skill folder is not revealed, try ~/.claude/skills/, ~/.openclaw/skills/, ~/.copilot/skills/, each with and without the jgs-se-knowledge-packs/ namespace. Transform index files live at ~/.codex/prompts/<slug>.md, ~/.gemini/commands/jgs-se-knowledge-packs/<slug>.toml, and ./.cursor/rules/<slug>.mdc.

Narrow consults read in the main thread on every host. A missing routed pack is noted and skipped; if none remain, fall back to route-only.

Scope & Limits

  • No SE claim without a citation from a pack file read this session.
  • The map is curated, not exhaustive. Agency rows are a filter, not an endorsement.
  • At most six packs per Topics row. At most four packs read per answer.
  • Deliverable stage chains come only from Deliverables rows; empty cells skip that stage.
  • /se never overwrites an existing file without a yes at a gate.

Orchestrator content © JG Systems Consulting Ltd. (MIT). Pack names and source titles are identified for routing only; each pack keeps its own licence.

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 Se AI skill do?

Orchestrator (not a knowledge pack): routes a free-text systems-engineering question to the right catalogue pack(s), reads them with you, and answers with pack and chapter citations. Runs only on explicit `/se <question>`; carries no source content. Use when you do not know which `/pack` to ask.

Why use Se on TypingMind?

Because you install it once and use it with any model. Se 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 Se in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/se. 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 Se?

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 Se?

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

Is the Se 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 👇