Install
$ agentstack add mcp-cavoiie-fluent-cfd-skill ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
.
+-- 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:
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_pythonMCP 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
- Source: cavoiie/fluent-cfd-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.