# Fluent Cfd Skill

> A Codex skill for Ansys Fluent and PyFluent CFD workflows.

- **Type:** MCP server
- **Install:** `agentstack add mcp-cavoiie-fluent-cfd-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [cavoiie](https://agentstack.voostack.com/s/cavoiie)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [cavoiie](https://github.com/cavoiie)
- **Source:** https://github.com/cavoiie/fluent-cfd-skill

## Install

```sh
agentstack add mcp-cavoiie-fluent-cfd-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Fluent CFD Skill

English | [简体中文](README.zh-CN.md)

A Codex skill for Ansys Fluent, PyFluent, and CFD simulation workflows.

This repository packages a research-oriented workflow skill for working with Fluent cases, solver setup, convergence diagnosis, and PyFluent MCP automation. It is designed as a judgment layer for agents: it does not replace the Fluent manuals, and it does not bundle a Fluent runtime.

## Highlights

- Fluent workflow discipline from problem framing to validation.
- PyFluent MCP tool-use guidance for safe, auditable Fluent automation.
- Convergence checks that combine residuals, monitors, conservation, and physical plausibility.
- Practical references for solver choice, boundary conditions, turbulence, numerics, validation, and error recovery.
- Conservative defaults for research use: no arbitrary Python execution unless explicitly enabled in the local MCP server.

## Repository Layout

```text
.
+-- SKILL.md
+-- agents/
|   +-- openai.yaml
+-- references/
    +-- workflow.md
    +-- solver-selection.md
    +-- boundary-conditions.md
    +-- turbulence-and-wall-treatment.md
    +-- numerics-and-convergence.md
    +-- pyfluent-mcp.md
    +-- validation-checklist.md
    +-- error-recovery.md
```

`SKILL.md` is intentionally compact. It routes the agent through the core CFD workflow and points to focused references only when needed.

## Use Cases

- Plan a Fluent case setup before touching the solver.
- Review boundary conditions, mesh quality, and physical assumptions.
- Choose solver settings, turbulence models, wall treatment, and convergence criteria.
- Diagnose residual stalls, reversed flow, divergence, and launch/license failures.
- Guide PyFluent MCP workflows such as launch, read case, run TUI commands, iterate, save, and close.

## Prompt Templates

Use the standard templates in [PROMPTS.md](PROMPTS.md) for full CFD reviews, short daily checks, PyFluent MCP runs, and convergence diagnosis.

## Installation

Copy this folder to your Codex skills directory:

```powershell
Copy-Item -Recurse . "$env:USERPROFILE\.codex\skills\fluent-cfd"
```

After installation, Codex can trigger the skill when a task mentions Fluent, PyFluent, Fluent TUI, CFD simulation setup, mesh quality, boundary conditions, turbulence models, residual convergence, UDFs, or post-processing.

## Versioning

Versions are managed with GitHub Releases and semantic version tags. Use the latest release for a stable skill snapshot, and use `main` for active edits.

## Safety Notes

- Residual decrease alone is not convergence.
- Mesh quality, units, boundary consistency, and wall-resolution checks should not be skipped.
- Turbulence model changes should have a physical reason or validation goal.
- The optional `execute_python` MCP tool should stay disabled unless the local workflow is trusted.
- This repository contains only the skill. A separate local PyFluent MCP server is required for live Fluent control.

## Related Execution Layer

The skill is designed to pair with a local `pyfluent` MCP server that exposes tools such as `server_info`, `launch_fluent`, `read_case`, `run_tui`, `iterate`, `write_case_data`, `session_status`, and `exit_fluent`.

That execution layer is intentionally separate from this repository so this skill remains lightweight, portable, and safe to publish.

## Stars

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [cavoiie](https://github.com/cavoiie)
- **Source:** [cavoiie/fluent-cfd-skill](https://github.com/cavoiie/fluent-cfd-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-cavoiie-fluent-cfd-skill
- Seller: https://agentstack.voostack.com/s/cavoiie
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.