cfd-fluids
Deep integration with computational fluid dynamics tools for internal and external flow analysis
Best use case
cfd-fluids is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Deep integration with computational fluid dynamics tools for internal and external flow analysis
Teams using cfd-fluids should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cfd-fluids/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cfd-fluids Compares
| Feature / Agent | cfd-fluids | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Deep integration with computational fluid dynamics tools for internal and external flow analysis
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# CFD Analysis Skill
## Purpose
The CFD Analysis skill provides deep integration with computational fluid dynamics tools for internal and external flow analysis, enabling systematic setup, execution, and post-processing of fluid simulations.
## Capabilities
- ANSYS Fluent, CFX, OpenFOAM workflow automation
- Mesh generation for complex geometries (structured, unstructured)
- Turbulence model selection (k-epsilon, k-omega, SST, LES)
- Boundary condition specification (inlet, outlet, wall, symmetry)
- Steady-state and transient flow simulations
- Post-processing for pressure, velocity, and flow visualization
- Mesh independence studies and validation
- Pressure drop and flow coefficient calculations
## Usage Guidelines
### Pre-Processing
#### Geometry Preparation
1. **CAD Cleanup**
- Remove small features (< 3 cells)
- Fill gaps and holes
- Create smooth transitions
- Define fluid domain boundaries
2. **Domain Definition**
- Internal flow: Extract fluid volume
- External flow: Create far-field boundary
- Symmetry: Identify planes of symmetry
- Periodic: Define periodic pairs
#### Mesh Generation
1. **Mesh Types**
| Type | Application | Pros/Cons |
|------|-------------|-----------|
| Structured hex | Simple geometries | High quality, more effort |
| Unstructured tet | Complex geometries | Flexible, more cells |
| Polyhedral | Complex internal | Good quality, moderate count |
| Hybrid | Mixed regions | Optimized for accuracy |
2. **Boundary Layer Mesh**
```
First cell height: y+ = 1 (wall-resolved)
y+ = 30-300 (wall functions)
y = y+ * mu / (rho * u_tau)
u_tau = sqrt(tau_w / rho)
```
3. **Mesh Quality Criteria**
```
Orthogonality: > 0.1 (> 0.3 preferred)
Skewness: < 0.95 (< 0.8 preferred)
Aspect ratio: < 100 (< 20 near walls)
```
### Solver Configuration
#### Turbulence Models
| Model | Application | Wall Treatment |
|-------|-------------|----------------|
| k-epsilon Standard | General industrial | Wall functions |
| k-epsilon Realizable | Rotation, separation | Wall functions |
| k-omega SST | Aerospace, separation | Low-Re or wall functions |
| Spalart-Allmaras | External aero | Low-Re |
| LES/DES | Unsteady, vortex shedding | Wall-resolved |
#### Boundary Conditions
1. **Inlet Conditions**
- Mass flow rate or velocity
- Turbulence intensity (1-5% typical)
- Hydraulic diameter or length scale
- Temperature (if energy equation)
2. **Outlet Conditions**
- Pressure outlet (most common)
- Outflow (fully developed)
- Mass flow outlet (specified)
3. **Wall Conditions**
- No-slip (default)
- Roughness (if significant)
- Thermal (adiabatic, fixed T, heat flux)
#### Solution Settings
1. **Discretization Schemes**
```
Convection: Second-order upwind (accuracy)
First-order (stability)
Pressure: PRESTO (complex geometry)
Standard (simple geometry)
```
2. **Convergence Criteria**
```
Residuals: < 1e-4 (typical)
< 1e-6 (high accuracy)
Monitor: Mass imbalance < 0.1%
Force convergence
```
### Post-Processing
1. **Flow Visualization**
- Streamlines and pathlines
- Velocity vectors
- Contour plots (P, V, T)
- Surface integral reports
2. **Quantitative Results**
- Pressure drop
- Flow coefficient (Cv)
- Heat transfer coefficient
- Force and moment
## Process Integration
- ME-010: Computational Fluid Dynamics (CFD) Analysis
## Input Schema
```json
{
"geometry": "CAD file path",
"flow_type": "internal|external",
"fluid": {
"name": "string",
"density": "number (kg/m3)",
"viscosity": "number (Pa.s)",
"specific_heat": "number (J/kg.K, if thermal)"
},
"inlet": {
"type": "velocity|mass_flow|pressure",
"value": "number",
"temperature": "number (K, if thermal)"
},
"outlet": {
"type": "pressure|outflow",
"value": "number (if pressure)"
},
"analysis_type": "steady|transient",
"turbulence_model": "k-epsilon|k-omega-sst|spalart-allmaras|laminar"
}
```
## Output Schema
```json
{
"flow_results": {
"pressure_drop": "number (Pa)",
"flow_coefficient": "number (Cv)",
"max_velocity": "number (m/s)",
"reynolds_number": "number"
},
"forces": {
"drag": "number (N)",
"lift": "number (N)",
"moment": "array [Mx, My, Mz]"
},
"thermal_results": {
"heat_transfer_rate": "number (W)",
"average_htc": "number (W/m2.K)",
"outlet_temperature": "number (K)"
},
"mesh_statistics": {
"cell_count": "number",
"y_plus_range": [min, max],
"orthogonality_min": "number"
},
"convergence": {
"iterations": "number",
"residuals": "object",
"mass_imbalance": "number"
}
}
```
## Best Practices
1. Always perform mesh independence study
2. Verify y+ values match turbulence model requirements
3. Monitor mass and energy imbalance
4. Validate with experimental data when available
5. Start with steady-state before transient
6. Use appropriate turbulence model for flow physics
## Integration Points
- Connects with CAD Modeling for geometry
- Feeds into Thermal Analysis for conjugate heat transfer
- Supports Heat Exchanger Design for performance prediction
- Integrates with Test Correlation for validationRelated Skills
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.
issue
Run an issue-centric Babysitter workflow.