Workbench Sim logo

Workbench Sim

Organization
svd-ai-lab
workbench-sim

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to connect to Ansys Workbench through sim-cli. Supports Workbench journal execution, project inspection, persistent sessions, Mechanical handoff, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned Ansys installation.

Overview

Publishersvd-ai-lab
Repositorysim-cli
Skill nameworkbench-sim
Stars
242
Forks
23
Bundled files
24
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.

  • 24 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 Workbench 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/workbench/src/sim_plugin_workbench/_skills/workbench
  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/workbench/src/sim_plugin_workbench/_skills/workbench .claude/skills/workbench-sim
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workbench 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 Workbench 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 Workbench 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.

workbench-sim

You are connected to Ansys Workbench via sim-cli. This file is the index. It tells you where to look for actual content — it does not contain the content itself.

The /connect response told you which active layers apply via:

json
"skills": {
  "root":               "<sim-skills>/workbench",
  "active_sdk_layer":   "0.4",
  "active_solver_layer": "24.1"
}

Always read the index for base/, then your active sdk/<version>/, then your active solver/<version>/. Later layers override earlier ones on identically-named files.


base/ — always relevant

Concepts, API patterns, and version-agnostic reference:

PathWhat's there
base/reference/pyworkbench_api.mdPyWorkbench SDK API surface: launch_workbench, run_script_string, upload_file, download_file, start_mechanical_server, start_fluent_server. Read first.
base/reference/journal_scripting.mdIronPython .wbjn scripting reference: SetScriptVersion, GetTemplate, CreateSystem, GetContainer, and the result file convention.
base/reference/system_templates.mdLive template discovery and resolver workflow. Template names are product/configuration dependent; treat any examples as non-authoritative.
base/reference/file_transfer.mdFile upload/download patterns between client and server.
base/reference/sub_solver_integration.mdStarting PyMechanical, PyFluent, PySherlock servers from within a Workbench session.
base/snippets/Numbered IronPython journal snippets (01 through 05). Each writes results to %TEMP%/sim_wb_result.json.
base/examples/Official PyWorkbench examples from pyansys.com — Fluent workflow, PyMechanical integration, logging, cooled turbine blade, cyclic symmetry, axisymmetric rotor, material designer.
base/workflows/static_structural/Validation guidance for Static Structural workflows. Use the API reference and snippets to build the intended project.
base/workflows/project_review_loop.mdRequired checkpoint loop: inspect health, project identity, systems summary, then run one bounded journal step.
base/workflows/debug_failed_exec.mdFailure triage loop for failed Workbench snippets and RunWB2 journals.
base/workflows/mechanical_handoff.mdWorkbench-to-Mechanical checklist for Static Structural workflows.
base/known_issues.mdVendor quirks, SDK version constraints, IronPython limitations.

sdk/<active_sdk_layer>/ — PyWorkbench SDK specifics

  • sdk/0.4/ — Minimum SDK for Ansys 24.1.
    • notes.md — release parameter (not version), missing methods vs 0.10+.
  • sdk/0.10/ — Modern SDK (requires Ansys >= 24.2).
    • notes.md — New APIs (download_project_archive, stop_*_server), version gate.

solver/<active_solver_layer>/ — Ansys release specifics

  • solver/24.1/ — Ansys 2024 R1.
    • notes.md — IronPython .NET 4.x constraints, SDK 0.4-0.9 only.

Hard constraints (apply to every session)

  1. Never call launch_workbench() from a snippet. sim-cli already started the Workbench session. A second launch spawns a conflicting server process.
  2. All snippets are IronPython journals, not Python SDK calls. The driver's run() method sends code through run_script_string() to the Workbench IronPython sandbox. Use Workbench API calls (SetScriptVersion, GetTemplate, etc.), not ansys.workbench.core.
  3. Results go through file convention. IronPython stdout is not piped. Write JSON to %TEMP%/sim_wb_result.json for the driver to read back.
  4. Never invent Category A defaults. Geometry, materials, BCs, acceptance criteria — if missing, ask the user.
  5. Acceptance ≠ exit code. Validate against physics-based criteria (e.g., component count, temperature range), not just exit code.
  6. Workbench owns cells 1-3. Engineering Data, Geometry, and Model orchestration belongs here. Mechanical setup, solve, and results belong to solver=mechanical.
  7. Resolve templates dynamically. Before creating any Workbench system, query the live session with workbench.templates.visible and workbench.templates.resolve:<intent>. If resolution fails, compare the live template list with official PyWorkbench examples/docs instead of copying a template table into the skill.

Required protocol (one paragraph)

After /connect succeeds: read base/reference/pyworkbench_api.md, base/reference/journal_scripting.md, base/reference/system_templates.md, and base/workflows/project_review_loop.md. Inspect session.health, workbench.project.identity, workbench.systems.summary, and the relevant template resolver result before creating a system. Execute IronPython journals incrementally via uv run sim exec, checking last.result and workbench.systems.summary after every step. Use snippets from base/snippets/ adapted to the user's task. Before handoff, read base/workflows/mechanical_handoff.md and confirm Workbench has a refreshed Model cell. Mechanical owns setup, solve, and result extraction.

Source

Canonical repository: svd-ai-lab/sim-plugin-workbench. Skill path: src/sim_plugin_workbench/_skills/workbench.

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 Workbench Sim AI skill do?

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to connect to Ansys Workbench through sim-cli. Supports Workbench journal execution, project inspection, persistent sessions, Mechanical handoff, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned Ansys installation.

Why use Workbench Sim on TypingMind?

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

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

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

Is the Workbench 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 👇