⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
mbse-diagramming
Create or review source-linked engineering architecture, workflow, sequence or state diagrams in Mermaid, Graphviz or an available UML/PlantUML tool skill; preserve semantics and report actual rendering checks.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Develop engineering artifacts with reliability, traceability, auditability and clear communication as explicit goals. This collection helps your chosen agent turn engineering questions into reviewable requirements, architecture, verification plans and change-impact reports.
16 skills cover core systems engineering practices, with optional OOSEM, SysML v2/KerML and visualization extensions. The core works with prose and tables; SysML and an engine are optional.
Explore the skills ecosystem
Interactive bubble map · Full-size SVG · Sources and maintenance
Explore all 16 skills and 14 related concepts. Select a category to zoom, search by name or purpose, and filter available skills, profile conventions, human responsibility, proposed roles or unimplemented methods. Each entry links to its source and states its limitations. Download the HTML and open it in a browser; GitHub displays HTML source.
The map groups entries for browsing; it does not change catalog layers or define execution dependencies. Circle sizes are decorative. Profiles are project-owned conventions, and the dashed agent/method bubbles represent proposals or gaps rather than shipped implementations.
Engineers remain responsible. Skills and agents support engineering judgment. When an unresolved assumption, acceptance criterion or source of authority could change the result, they should ask for clarification rather than silently decide. Changed engineering artifacts require review by the responsible human before adoption; passing checks or agreement among agents do not establish acceptance. Drafting and investigation can continue within the authorized scope while dependent decisions remain open.
Engineering principles
The collection takes its direction from the discipline required for mission-critical systems: make obligations explicit, expose uncertainty, preserve evidence and keep engineering decisions accountable.
| Principle | What it means in the artifacts |
|---|---|
| Reliability and assurance | Measurable obligations, explicit operating assumptions, bounded checks and visible failure or inconclusive outcomes |
| Traceability | Stable identities and relationships from needs and assumptions through requirements, architecture, checks and evidence |
| Auditability | Source references, decision status, native observations and artifact identities that a reviewer can inspect |
| Reproducibility and configuration control | Recorded model/tool versions, preserved inputs and explicit review of stale evidence after changes |
| Clear engineering communication | Audience-appropriate views, units, system boundaries and an explanation of what each result establishes |
| Verification and validation | Separate evidence that a stated obligation is met from evidence that the system serves its intended use |
| Human accountability | Proposed agent outputs remain distinct from decisions made by identified engineering authorities |
Read the engineering principles and review questions. This early-draft collection supports these practices; it is not a qualified toolchain, safety case or evidence that a system is ready for mission-critical use.
Start here
| You want to… | Start with |
|---|---|
| Complete your first engineering task | Engine-free walkthrough |
| Find the right skill for existing work | Task-based skill guide |
| Inspect an end-to-end example | Rover project and retained evidence |
| Configure local model checks | Engine setup and development |
| Find engines, editors or model services | Awesome SysML v2 & MBSE |
Install and try a first task
Onboarding has three steps: copy the skills into your project, ask the setup skill to record your conventions, then choose one engineering task. Start with Markdown and tables; add a modeling language or engine when the task needs it. Setup adapts an established project's conventions and can use the editable starter for a new project.
When your team's practice is unresolved, setup starts by asking what you follow today, then offers tailored core practices, the bounded OOSEM adaptation, or your existing team process. It records the selection and tailoring in your project conventions. ICONIX and other unimplemented methodologies remain visible as coverage gaps, rather than ready-made options. Installation alone does not launch this interview; invoke setup in your chosen agent.
Requires Node.js/npm for installation. From your target engineering project:
npx [email protected] add DynamicalSystemsGroup/mbse_skills --agent codex --skill '*' --copy
This copies all 16 skills into project-local .agents/skills. Version 1.7.0 is the tested installer. No repository clone or Python environment is needed for installation. Then ask your agent:
Use setup-mbse-skills to configure this project for an illustrative rover energy-budget task. Use Markdown and tables, with tools unconfigured. Record the system boundary, assumptions, requirements and evidence conventions, then identify one requirement to develop with mbse-requirements. Keep all engineering choices proposed until reviewed.
For your own project, start with: “Use setup-mbse-skills to learn our engineering practice, show the supported methodology choices, and tailor the project conventions and first task to our selection.” Existing choices are preserved; setup asks about missing decisions one main question at a time.
Follow the first-task walkthrough for the inputs, next prompt, expected files and completion checks. Selective installation, plugin and manual-copy alternatives are in distribution and onboarding.
Customize for your team
The copied skills are ordinary editable files. Choose the practices you need and adapt them to your project; you can begin with a single task without adopting the entire workflow.
| Customize | Where to make the choice |
|---|---|
| Document locations, IDs, vocabulary and review responsibilities | Project-owned conventions, normally docs/mbse-project.md |
| Methodology and model representation | Select core practices and optional extensions in the task guide; prose and tables remain valid |
| Evidence storage, verification expectations and existing tools | Project conventions, with lo |
// HOW IT'S BUILT
KEY FILES