cad-modeling

Expert skill for parametric 3D CAD model development with design intent and configuration management

509 stars

Best use case

cad-modeling is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Expert skill for parametric 3D CAD model development with design intent and configuration management

Teams using cad-modeling 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

$curl -o ~/.claude/skills/cad-modeling/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/domains/science/mechanical-engineering/skills/cad-modeling/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/cad-modeling/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How cad-modeling Compares

Feature / Agentcad-modelingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Expert skill for parametric 3D CAD model development with design intent and configuration management

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

# 3D CAD Modeling Skill

## Purpose

The 3D CAD Modeling skill provides expert capabilities for parametric 3D CAD model development with proper design intent, configuration management, and best practices for model quality and reusability.

## Capabilities

- SolidWorks, CATIA, NX, Creo workflow automation
- Parametric feature-based modeling best practices
- Assembly design and constraint management
- Design table and configuration creation
- Top-down and bottom-up assembly strategies
- Part family and library component creation
- Model validation and quality checking
- CAD data exchange and translation

## Usage Guidelines

### Part Modeling

#### Design Intent Capture

1. **Sketch Best Practices**
   - Fully constrain all sketches
   - Use construction geometry
   - Apply meaningful dimensions
   - Reference design features, not edges

2. **Feature Planning**
   ```
   Order of features:
   1. Primary form (base feature)
   2. Secondary forms
   3. Positioned features
   4. Detail features (rounds, chamfers)
   5. Reference geometry
   ```

3. **Parametric Relationships**
   - Link related dimensions
   - Use equations for complex relationships
   - Create global variables for key parameters
   - Document design equations

#### Feature Best Practices

| Feature Type | Best Practice |
|--------------|---------------|
| Extrude | Use mid-plane when symmetric |
| Revolve | Full 360 or symmetric angle |
| Sweep | Keep profile perpendicular to path |
| Loft | Match profile vertex count |
| Fillet | Apply late in feature tree |
| Pattern | Use linear/circular for regular arrays |

#### Model Quality

1. **Geometry Checks**
   - No self-intersecting geometry
   - Minimum wall thickness maintained
   - Draft analysis for molded parts
   - Undercut detection

2. **File Management**
   - Meaningful part names
   - Custom properties populated
   - Revision history maintained
   - Linked reference files documented

### Assembly Modeling

#### Assembly Strategies

1. **Bottom-Up Assembly**
   - Components modeled independently
   - Assembled using mates/constraints
   - Best for: Standard components, reusable parts

2. **Top-Down Assembly**
   - Layout sketch defines relationships
   - Parts reference assembly geometry
   - Best for: Highly integrated systems

3. **Hybrid Approach**
   - Combine strategies as appropriate
   - Use skeleton/layout for key interfaces
   - Independent modeling for standard parts

#### Mate/Constraint Best Practices

1. **Constraint Types**
   | Type | Use Case |
   |------|----------|
   | Coincident | Face-to-face contact |
   | Concentric | Shaft/hole alignment |
   | Distance | Offset positioning |
   | Angle | Angular relationship |
   | Tangent | Curved surface contact |

2. **Degree of Freedom**
   - Fully constrain or document remaining DOF
   - Use limit mates for motion range
   - Consider mechanism simulation needs

#### Large Assembly Management

1. **Performance Optimization**
   - Use lightweight/simplified representations
   - Create configurations for assembly states
   - Suppress unused components
   - Use envelope geometry for space claims

2. **Reference Management**
   - Minimize external references
   - Document all in-context relationships
   - Use published geometry when possible

### Configuration Management

1. **Part Configurations**
   - Variations: Sizes, materials, features
   - Design table for multiple configurations
   - Display states for visualization

2. **Assembly Configurations**
   - Bill of materials variations
   - Exploded views
   - Suppressed component states

## Process Integration

- ME-003: 3D CAD Model Development

## Input Schema

```json
{
  "part_type": "component|assembly|drawing",
  "design_requirements": {
    "function": "string",
    "envelope": {
      "length": "number (mm)",
      "width": "number (mm)",
      "height": "number (mm)"
    },
    "interfaces": "array of interface definitions",
    "material": "string"
  },
  "reference_geometry": "file path or description",
  "configurations_needed": "array of configuration names",
  "manufacturing_method": "machined|cast|molded|sheet_metal|additive"
}
```

## Output Schema

```json
{
  "model_info": {
    "file_path": "string",
    "file_format": "native|STEP|IGES",
    "revision": "string"
  },
  "geometry_summary": {
    "bounding_box": "object",
    "volume": "number (mm3)",
    "surface_area": "number (mm2)",
    "mass": "number (kg)"
  },
  "quality_check": {
    "fully_constrained": "boolean",
    "no_errors": "boolean",
    "rebuild_time": "number (s)"
  },
  "configurations": "array of config names",
  "custom_properties": "object"
}
```

## Best Practices

1. Plan feature order before modeling
2. Use symmetric features when design is symmetric
3. Avoid external references when possible
4. Create reusable part templates
5. Document design intent in model notes
6. Validate geometry before release

## Integration Points

- Connects with Requirements Flowdown for design inputs
- Feeds into GD&T Drawing for documentation
- Supports FEA Structural for analysis
- Integrates with DFM Review for manufacturability

Related Skills

topic-modeling-text-mining

509
from a5c-ai/babysitter

Apply LDA, NMF, and other computational methods to discover patterns in large text corpora with appropriate parameter tuning

stan-bayesian-modeling

509
from a5c-ai/babysitter

Stan probabilistic programming for Bayesian inference

hydrologic-modeling-engine

509
from a5c-ai/babysitter

Hydrologic modeling skill for rainfall-runoff analysis, flood frequency, and watershed analysis

media-mix-modeling

509
from a5c-ai/babysitter

Advanced econometric modeling for marketing effectiveness and budget optimization

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/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

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.

retrospect

509
from a5c-ai/babysitter

Summarize or retrospect on a completed Babysitter run.

resume

509
from a5c-ai/babysitter

Resume an existing Babysitter run from Codex.

project-install

509
from a5c-ai/babysitter

Install the Babysitter Codex workspace integration into the current project.