Run Fluent Autoclave logo

Run Fluent Autoclave

CommunityPopular
Cai-aa
run-fluent-autoclave

Run, diagnose, reproduce, and validate ANSYS Fluent CFD simulations of forced-convection autoclaves using Fluent MCP or PyFluent. Use for autoclave or hot-air vessel projects involving SCDOC/STEP geometry, annular velocity inlets, pressure outlets, Spalart-Allmaras turbulence, energy transport, calorimeter temperature boundaries, automatic meshing, longitudinal velocity contours, streamlines, mass-balance checks, or the Bohne paper boundary-condition case.

Overview

PublisherCai-aa
RepositoryCAE-Agent-Hub
Skill namerun-fluent-autoclave
Stars
1K
Forks
130
Bundled files
7
LicenseMIT
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.

  • 7 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 Run Fluent Autoclave 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/Cai-aa/CAE-Agent-Hub/tree/main/Skill/Ansys/run-fluent-autoclave
  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/Cai-aa/CAE-Agent-Hub.git /tmp/CAE-Agent-Hub
mkdir -p .claude/skills
cp -r /tmp/CAE-Agent-Hub/Skill/Ansys/run-fluent-autoclave .claude/skills/run-fluent-autoclave
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Run Fluent Autoclave 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 Run Fluent Autoclave 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 Run Fluent Autoclave 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.

Run Fluent Autoclave

Reproduce the validated open autoclave workflow while preserving geometry-specific judgment and numerical evidence.

Workflow

  1. Detect Fluent before launching it. Confirm fluent.exe, PyFluent, version, and job directory.
  2. Inspect the geometry and existing project files. Reuse a valid STEP/fluid domain instead of rebuilding geometry.
  3. Read references/paper-case.md before applying the Bohne-style boundary conditions.
  4. Read references/mcp-workflow.md before controlling Fluent MCP or handling a Chinese path.
  5. Copy the bundled scripts into the job directory and adjust only the geometry-dependent constants.
  6. Generate and check the mesh. Reject unmatched boundary faces, non-manifold faces, invalid volumes, or a misidentified full-face inlet.
  7. Configure Fluent in small validated chunks. Print each model, material, and boundary state after setting it.
  8. Run one time step first. Continue only if the mesh is valid and residuals remain finite.
  9. Run the remaining steps asynchronously when possible, monitor stdout/stderr, and save case/data before post-processing.
  10. Extract mass flow, inlet/outlet average and maximum speeds, global maximum speed and location, pressure drop, temperature range, and the final residuals.
  11. Generate the vertical longitudinal mid-plane velocity contour and streamlines with outlet left and inlet/head right.
  12. Run scripts/validate_results.py on the final JSON. Do not call the result complete if conservation or provenance checks fail.

Required physical setup

  • Use the annular clearance at the ellipsoidal head as the velocity inlet; never use the whole end face without verifying the geometry.
  • Use a pressure outlet at the opposite duct.
  • Keep vessel walls adiabatic and no-slip.
  • Split exposed calorimeter faces into a separate fixed-temperature wall zone.
  • Use the material properties and boundary values in references/paper-case.md when reproducing that case.
  • Treat the reference image peak velocity as an outcome, not a prescribed outlet value.

Reliability rules

  • Preserve prior cases and results; write the new run under distinct names.
  • Prefer named zones over raw zone IDs after the mesh is loaded.
  • Verify the global maximum location. A maximum at the outlet is suspicious unless the geometry physically contracts there.
  • Report local outlet reverse-flow area separately from net mass conservation.
  • State geometry-scale differences before comparing peak speeds to a paper.
  • Do not report wall heat-transfer coefficients as design values without a near-wall mesh and y-plus assessment.
  • Keep the final Fluent MCP session loaded when the user is likely to continue interactively.

Bundled scripts

  • scripts/mesh_autoclave_paper_case.py: Boolean fluid-domain construction, boundary splitting, and refined tetrahedral mesh.
  • scripts/prepare_fluent_paper_mesh.py: Deterministic Gmsh-to-Fluent ASCII mesh conversion with named zones.
  • scripts/plot_fluent_paper_results.py: Main-view velocity, streamline, temperature, and pressure figures from extracted plane data.
  • scripts/validate_results.py: Acceptance checks for the final result JSON.

The three simulation scripts are validated against the supplied autoclave topology. Inspect and adapt their STEP volume ordering, coordinate tests, and output paths for a different geometry.

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 Run Fluent Autoclave AI skill do?

Run, diagnose, reproduce, and validate ANSYS Fluent CFD simulations of forced-convection autoclaves using Fluent MCP or PyFluent. Use for autoclave or hot-air vessel projects involving SCDOC/STEP geometry, annular velocity inlets, pressure outlets, Spalart-Allmaras turbulence, energy transport, calorimeter temperature boundaries, automatic meshing, longitudinal velocity contours, streamlines, mass-balance checks, or the Bohne paper boundary-condition case.

Why use Run Fluent Autoclave on TypingMind?

Because you install it once and use it with any model. Run Fluent Autoclave 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 Run Fluent Autoclave in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Cai-aa/CAE-Agent-Hub/tree/main/Skill/Ansys/run-fluent-autoclave. 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 Run Fluent Autoclave?

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 Run Fluent Autoclave?

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

Is the Run Fluent Autoclave 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

Set up your own AI workspace now

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