Flotherm Sim logo

Flotherm Sim

Organization
svd-ai-lab
flotherm-sim

Run, inspect, or troubleshoot Simcenter Flotherm thermal cases using the smallest verified local control path. Use for Flotherm installation checks, existing-project re-solves, .pack import, FloSCRIPT playback, model creation or modification, solver monitoring, and result extraction. Discover native and sim-cli capabilities before choosing a path; do not assume either is installed or connected.

Overview

Publishersvd-ai-lab
Repositorysim-cli
Skill nameflotherm-sim
Stars
242
Forks
23
Bundled files
16
LicenseApache-2.0
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.

  • 16 bundled files

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

  • Open source

    Published by svd-ai-lab on GitHub. Read the source before you install it.

Installation

Install the Flotherm Sim 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/svd-ai-lab/sim-cli/tree/main/plugins/flotherm/src/sim_plugin_flotherm/_skills/flotherm
  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/svd-ai-lab/sim-cli.git /tmp/sim-cli
mkdir -p .claude/skills
cp -r /tmp/sim-cli/plugins/flotherm/src/sim_plugin_flotherm/_skills/flotherm .claude/skills/flotherm-sim
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Flotherm Sim 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 Flotherm Sim 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 Flotherm Sim 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.

Flotherm

Control Simcenter Flotherm through the narrowest path that can produce the requested evidence. A bundled skill does not prove that Flotherm, a license, sim-cli-core, or sim-plugin-flotherm is installed.

Start with capability discovery

Use one or two bounded probes before choosing an execution path:

  1. Identify the requested operation and input:
    • installation or version lookup
    • unchanged existing-project re-solve
    • .pack import
    • first-time model creation or modification
    • solve monitoring or result extraction
  2. Inspect the current runtime directly:
    • Flotherm install roots, flotherm.bat, translator.exe, and solexe.exe
    • the requested project, .pack, FloSCRIPT, logs, and result directories
    • interactive Windows desktop availability for GUI automation
    • an already available sim command or matching project environment
  3. Choose a path from the table below. Do not install or download sim-cli merely to answer an availability, location, version, or saved-result question.

Do not infer that Flotherm is unavailable from a missing sim command. Do not search transient package-manager caches for old sim.exe files as a normal discovery path.

Choose the execution path

TaskPreferred pathWhy
Locate Flotherm or report its versionDirect filesystem, environment, or Registry probeNo control runtime is needed
Inspect saved logs or result fieldsDirect file readingAvoid launching the solver
Re-solve an existing, unchanged project in FLOUSERDIRNative translator.exe + solexe.exeVerified headless path
Import a .pack, create a project, or modify model inputssim-cli GUI automationFlotherm 2504 command-line FloSCRIPT playback is not verified end to end
Diagnose driver/session health or capture structured GUI evidenceExisting sim-cli sessionUses the plugin's session and diagnostic surfaces

If the selected path requires sim-cli but the command or Flotherm plugin is missing, explain the requirement and get the user's approval before downloading or installing packages. Prefer the user's existing project environment and a pinned public package source. Do not silently use a repository main branch for an ephemeral install.

Native batch re-solve

Use this only for an existing project that has already been imported or created in FLOUSERDIR and does not need parameter or geometry changes:

batch
call flotherm.bat -env
translator.exe -p "<FLOUSERDIR>\<project>.<GUID>" -n1
solexe.exe -p "<FLOUSERDIR>\<project>.<GUID>"

The native path can re-solve an existing project, including a crash-recovery rerun. It cannot import a .pack, create a project, or apply model changes.

Check the project log at DataSets/BaseSolution/PDTemp/logit and the expected result fields under DataSets/BaseSolution/msp_*/end/. Process exit alone is not engineering acceptance.

sim-cli GUI automation

Use this path when the task needs .pack import, FloSCRIPT playback, first-time creation, or model modification. It requires an interactive Windows desktop; Flotherm's Qt UI automation does not work in a non-interactive SSH session.

Use the package manager and environment already selected by the user. Typical commands, once sim and the matching plugin are verified, are:

powershell
uv run sim check flotherm
uv run sim connect --solver flotherm --ui-mode gui
uv run sim exec '<path>.pack'
uv run sim exec 'solve'
uv run sim exec 'status'
uv run sim disconnect

Keep the returned session id and pass it explicitly when commands do not share environment state. Let the driver own the Flotherm process while UI automation is active; concurrent user input can race with UI element discovery.

For model generation, write and lint small FloSCRIPT XML steps, execute one step at a time, and save a project checkpoint after each successful mutation. Read base/reference/floscript_modeling.md before authoring FloSCRIPT.

Failure and retry rules

  • Preserve the first failing command, status, logs, and screenshot before attempting a workaround.
  • After a GUI playback failure, inspect the session once and capture one visual or log artifact when useful. Do not repeat an equivalent exec call unless a specific state change addresses the failure.
  • Treat a missing file dialog, wrong foreground window, session mismatch, and non-interactive desktop as distinct failure classes.
  • Use plugin doctor --deep only for a suspected plugin or protocol defect, not as a routine response to a solver/UI failure.
  • Stop and report when the chosen path is unsupported, installation would be required without approval, or one bounded diagnostic cycle does not identify a corrective action.
  • Disconnect only the session owned by the task. Do not terminate every process matching a generic Flotherm executable name.

Validation and evidence

Before mutation or solve:

  • confirm the exact input/project and Flotherm version
  • confirm that the chosen path supports the requested operation
  • define a result-based acceptance criterion
  • lint FloSCRIPT or inspect the existing project when applicable

Before claiming completion:

  • verify Flotherm's completion or convergence marker
  • inspect expected project, log, and result artifacts
  • extract a numeric engineering result when the task calls for one
  • report the execution path used and any checks that were skipped

For GUI solves, look for the Flotherm message indicating that the steady solver stopped after convergence. For result extraction, read base/reference/postprocessing.md. For acceptance details, read base/reference/acceptance_checklists.md.

Load additional guidance only when needed

  • FloSCRIPT modeling: base/reference/floscript_modeling.md
  • Result extraction: base/reference/postprocessing.md
  • Error-code triage: base/reference/error_codes.md
  • Headless authoring limitations: base/reference/headless_bootstrap_investigation.md
  • Runtime control patterns: base/reference/runtime_patterns.md
  • Known driver and vendor issues: known_issues.md
  • Release-specific differences: solver/<detected-version>/notes.md

The version-specific layer is useful only after the installed Flotherm release has been detected. Do not assume a /connect response or active solver layer exists before capability discovery.

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 Flotherm Sim AI skill do?

Run, inspect, or troubleshoot Simcenter Flotherm thermal cases using the smallest verified local control path. Use for Flotherm installation checks, existing-project re-solves, .pack import, FloSCRIPT playback, model creation or modification, solver monitoring, and result extraction. Discover native and sim-cli capabilities before choosing a path; do not assume either is installed or connected.

Why use Flotherm Sim on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/svd-ai-lab/sim-cli/tree/main/plugins/flotherm/src/sim_plugin_flotherm/_skills/flotherm. 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 Flotherm Sim?

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 Flotherm Sim?

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

Is the Flotherm Sim AI skill free?

Yes. It is published on GitHub by svd-ai-lab under the Apache-2.0 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

Set up your own AI workspace now

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