Cst Simulation Workflow

CommunityPopular

Cai-aa

cst-simulation-workflow

Use this skill when driving CST Studio Suite through the CST MCP for electromagnetic simulation workflows: creating or opening CST projects, resolving missing inputs, selecting templates, setting up geometry/materials/ports/boundaries/mesh/solvers/monitors, running or planning simulations, extracting S-parameters/far-field/near-field/eigenmode results, validating outputs, parameter sweeps, optimization handoff, and report generation.

Overview

Publisher	Cai-aa
Repository	`CAE-Agent-Hub`
Skill name	`cst-simulation-workflow`
Stars	1K
Forks	130
Bundled files	8
License	MIT
Links	Skill source Repository

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.
8 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Cai-aa on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Cai-aa/CAE-Agent-Hub/tree/main/Skill/CST/cst-simulation-workflow
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.

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/Cai-aa/CAE-Agent-Hub.git /tmp/CAE-Agent-Hub
mkdir -p .claude/skills
cp -r /tmp/CAE-Agent-Hub/Skill/CST/cst-simulation-workflow .claude/skills/cst-simulation-workflow

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cst Simulation Workflow 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 Cst Simulation Workflow 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 Cst Simulation Workflow 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.

CST Simulation Workflow

Use this skill as the workflow and decision layer. Use the CST MCP as the execution layer.

Prefer the repository CST MCP native tools for live session control. Use the vendored cst_runtime_* or cst_toolbox_* wrappers for larger command catalogs, workspace pipelines, result export, parameter sweeps, and optimization helpers.

Operating Modes

First classify the request:

Mode	Use when	Action
Plan only	User asks for a scheme, script outline, or workflow	Do not run CST; produce the setup plan and assumptions
New project	User wants a new CST case	Select a template, resolve inputs, create a run project
Existing project	User provides a `.cst` path or asks to modify an open project	Inspect first, then work on a copy unless explicitly told otherwise
Parameter sweep	User asks for ranges, cases, or comparison	Use sweep preview before running cases
Optimization	User asks to improve S11, gain, bandwidth, coupling, etc.	Hand off to runtime optimization workflow after confirming objective and bounds

Standard Workflow

Detect CST MCP availability and CST Design Environment status.
Determine whether to create a new project, open a copy of an existing .cst, or only generate a plan.
Identify the simulation class and select a template when appropriate.
Resolve missing inputs using the parameter policy.
Present a compact defaults card before expensive solves unless the user already said to use defaults or run directly.
Build or modify geometry, materials, coordinate system, ports/excitations, boundaries, mesh, solver, and monitors.
Save the working project before running a solver.
Run the solver only when the user requested execution or accepted the defaults.
Extract result tree items and export requested data.
Validate results against the objective and evidence requirements.
Generate a concise report with assumptions, files, commands/tools used, result paths, and validation status.
Close/cleanup the CST project/session and report any nonblocking residual locks or access-denied cleanup messages.

Reference Files

Read only the reference file needed for the current task:

references/workflow.md for the end-to-end workflow and mode-specific execution details.
references/parameter-policy.md for required questions, defaults, derived values, and existing-project inspection.
references/mcp-tool-map.md for this repository's CST MCP tool names and when to prefer native vs runtime tools.
references/templates.md for V1 simulation templates and default values.
references/result-validation.md for S-parameter, far-field, near-field, eigenmode, sweep, and report validation.
references/cst-red-lines.md for correctness and safety rules that must not be violated.

Input Policy

Ask at most one compact clarification when critical information is missing. If the user says "directly run", "use defaults", "先默认", or equivalent, use defaults and record them in the report.

Critical inputs that usually require confirmation:

simulation case type
target frequency or frequency band
new project vs existing project
primary result objective
whether to actually run the solver

Defaultable inputs include units, background, common metals, antenna boundaries, solver choice, monitor frequencies, mesh level, and standard result exports. See references/parameter-policy.md.

Execution Rules

Do not overwrite a user's source .cst project. Copy it to a run directory unless the user explicitly requests in-place edits.
Inspect existing projects before changing them.
Prefer CST Macro Recorder-style VBA history blocks for modeling operations when no higher-level MCP tool exists.
Save before solving.
Treat solver success as unverified until result files, result tree entries, or exported data confirm it.
For long or costly solves, state the assumptions and expected outputs before running.

Result Rules

Do not treat complex S-parameter values as dB. Convert with 20*log10(abs(S11)).
Do not report Abs(E) as gain. Use Realized Gain, Gain, or Directivity for far-field gain claims.
Keep model-building/session operations separate from result-reading operations when the tool surface exposes separate modes.
Include exact evidence paths for project files, exports, reports, and logs.

V1 Scope

Focus V1 on:

a single new standard antenna case, especially a 2.4 GHz Wi-Fi/IoT microstrip patch antenna;
opening an existing .cst, inspecting it, changing parameters, and rerunning on a copy;
S11, VSWR, far-field gain/directivity, radiation pattern, eigenmode frequency, and concise Markdown report outputs;
parameter sweep preview/run through the CST MCP sweep tools.

Use 77 GHz 1x4 radar patch array as a demonstration template after the basic workflow is stable.

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 Cst Simulation Workflow AI skill do?

Why use Cst Simulation Workflow on TypingMind?

Because you install it once and use it with any model. Cst Simulation Workflow 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 Cst Simulation Workflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Cai-aa/CAE-Agent-Hub/tree/main/Skill/CST/cst-simulation-workflow. 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 Cst Simulation Workflow?

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 Cst Simulation Workflow?

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

Is the Cst Simulation Workflow AI skill free?

Yes. It is published on GitHub by Cai-aa under the MIT license. 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

Brand Discovery

affaan-m

CommunityPopular

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Bun Runtime

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.

Competitive Report Structure

affaan-m

CommunityPopular

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space…

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

CST Simulation Workflow

Operating Modes

Standard Workflow

Reference Files

Input Policy

Execution Rules

Result Rules

V1 Scope

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now