Spaceclaim logo

Spaceclaim

Organization
svd-ai-lab
spaceclaim

Work with Ansys SpaceClaim or Discovery CAD geometry through local executables, SpaceClaim scripting/API, GUI-assisted workflows, or solver-prep handoff. Use when Codex needs to inspect, repair, defeature, import/export, script, extract enclosures or fluid domains, create named geometry, or prepare CAD for Fluent, Mechanical, COMSOL, or another solver.

Overview

Publishersvd-ai-lab
Repositorysim-cli
Skill namespaceclaim
Stars
242
Forks
23
Bundled files
3
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.

  • 3 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 Spaceclaim 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/spaceclaim/skills/spaceclaim
  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/spaceclaim/skills/spaceclaim .claude/skills/spaceclaim
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Spaceclaim 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 Spaceclaim 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 Spaceclaim 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.

SpaceClaim Skill

Use this skill for Ansys SpaceClaim CAD preparation and geometry automation. SpaceClaim is usually a desktop geometry/preprocessing tool, not the solver itself. Prefer the narrowest path that gives real evidence: file inspection for simple inventory, SpaceClaim scripts for repeatable geometry commands, GUI operation for semantic face/body choices, and solver-specific tools after the geometry is exported.

Working Approach

  1. Probe availability before launching SpaceClaim when local state is unknown.
    • Run scripts/probe_spaceclaim.ps1 when working on Windows.
    • Acceptable alternatives: Get-Command SpaceClaim.exe, common Ansys install-path checks, Registry checks, or a user-provided SIM_SPACECLAIM_ROOT.
    • Missing sim-cli, Python, or PyFluent is not evidence that SpaceClaim is missing; SpaceClaim often runs its own scripting host inside the desktop app.
  2. Inspect inputs before changing them.
    • List CAD files and sidecars.
    • For STEP, read the header/schema/unit lines and a small topology sample before opening the full model.
    • Prefer writing derived files beside the original CAD instead of in-place edits.
  3. Choose the control path by task.
    • Batch/script: imports, exports, simple body operations, repeatable named groups, repair sequences, or documented commands.
    • GUI-assisted: face selections, cap selections, seed points, periodic cuts, flow-path choices, or anything requiring design intent.
    • Solver handoff: meshing, boundary physics, convergence, and result validation belong in Fluent/Mechanical/COMSOL/etc. after CAD prep.
  4. After each meaningful change, verify the artifact rather than only the process exit. Check output file existence, format, units, body/face counts when available, and screenshots or exported geometry for visually sensitive work.
  5. Report uncertainty plainly. When the API cannot expose the geometry semantics needed for safe automation, produce a semi-automatic workflow or script template and identify the exact user selection still needed.

Common Workflows

Capability Probe

From PowerShell:

powershell
pwsh -NoProfile -ExecutionPolicy Bypass -File scripts/probe_spaceclaim.ps1

Use the JSON-like output to identify:

  • SpaceClaim executable path and Ansys version root.
  • Nearby scripting/API XML or CHM documentation.
  • Whether command names relevant to the task appear in local docs.

For a targeted check:

powershell
pwsh -NoProfile -ExecutionPolicy Bypass -File scripts/probe_spaceclaim.ps1 `
  -CommandNames VolumeExtract,Enclosure,NamedSelection,Export

Fluid Domain or Enclosure Extraction

Start with geometry evidence:

  • Which file is the single part/module versus assembly.
  • STEP units and whether closed shells/solids are present.
  • Which openings are inlets, outlets, vents, periodic cuts, or artificial manufacturing splits.

Use SpaceClaim VolumeExtract or Enclosure after the flow region is defined. Fully unattended extraction is most reliable for simple, unambiguous models. If inlet/outlet caps or seed points are ambiguous, switch to GUI-assisted operation and leave a script/workflow for the repeatable parts.

Export a solver-ready neutral file such as STEP, Parasolid, or a solver-native project, then hand off to the solver skill/tool for meshing and physics.

Scripted Geometry Edits

Prefer a small script that:

  1. Opens/imports the source file.
  2. Runs one class of operation.
  3. Creates named outputs or groups.
  4. Exports to a new file.
  5. Prints a short summary.

Before relying on a command signature, inspect the local versioned API docs or record a small operation in SpaceClaim's script recorder. SpaceClaim command surfaces differ by version and installation channel.

GUI-Assisted Work

Use the GUI when a person needs to decide design intent. Common GUI-driven selections include:

  • Selecting which faces are fuel inlet, oxidizer inlet, outlet, wall, symmetry, or periodic boundaries.
  • Choosing the internal cavity versus exterior air.
  • Defeaturing geometry where removing the wrong feature changes the physics.

The useful agent role is to prepare the file, propose the selections, drive or observe SpaceClaim where possible, and verify the exported geometry.

Evidence

  • A found executable proves installation, not licensing or script success.
  • A successful launch proves transport, not a valid CAD operation.
  • A generated script proves preparation, not completed geometry extraction.
  • A solver-ready export plus inspection evidence is the minimum proof that CAD prep completed.

For an agent-oriented assessment of SpaceClaim's API, read references/api-agent-assessment.md.

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 Spaceclaim AI skill do?

Work with Ansys SpaceClaim or Discovery CAD geometry through local executables, SpaceClaim scripting/API, GUI-assisted workflows, or solver-prep handoff. Use when Codex needs to inspect, repair, defeature, import/export, script, extract enclosures or fluid domains, create named geometry, or prepare CAD for Fluent, Mechanical, COMSOL, or another solver.

Why use Spaceclaim on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/svd-ai-lab/sim-cli/tree/main/plugins/spaceclaim/skills/spaceclaim. 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 Spaceclaim?

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 Spaceclaim?

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

Is the Spaceclaim 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 👇