vcad
Create 3D CAD models using vcad MCP tools. Use when the user asks to create 3D parts, mechanical components, plates with holes, brackets, or any parametric geometry. Supports primitives (cube, cylinder, sphere, cone), boolean operations, transforms, patterns, and export to STL/GLB.
Best use case
vcad is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create 3D CAD models using vcad MCP tools. Use when the user asks to create 3D parts, mechanical components, plates with holes, brackets, or any parametric geometry. Supports primitives (cube, cylinder, sphere, cone), boolean operations, transforms, patterns, and export to STL/GLB.
Teams using vcad 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/skill/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How vcad Compares
| Feature / Agent | vcad | 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?
Create 3D CAD models using vcad MCP tools. Use when the user asks to create 3D parts, mechanical components, plates with holes, brackets, or any parametric geometry. Supports primitives (cube, cylinder, sphere, cone), boolean operations, transforms, patterns, and export to STL/GLB.
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
# vcad - Parametric CAD for AI Agents
Create 3D CAD models programmatically using the vcad MCP tools.
## Available Tools
### create_cad_document
Build geometry from structured primitives and operations.
### export_cad
Export to STL (3D printing) or GLB (visualization).
### inspect_cad
Get volume, surface area, bounding box, and triangle count.
## Primitive Origins
Understanding where primitives are positioned is critical for correct placement:
| Primitive | Origin | Extent |
|-----------|--------|--------|
| Cube | Corner at (0,0,0) | Extends to (size.x, size.y, size.z) |
| Cylinder | Base center at (0,0,0) | Height along +Z |
| Sphere | Center at (0,0,0) | Radius in all directions |
| Cone | Base center at (0,0,0) | Height along +Z |
## Positioning Operations
The `at` parameter accepts three formats:
1. **Absolute**: `{x: 25, y: 15, z: 0}` - exact coordinates in mm
2. **Named**: `"center"`, `"top-center"`, `"bottom-center"` - relative to base primitive
3. **Percentage**: `{x: "50%", y: "50%"}` - percentage of base primitive bounds
## Common Patterns
### Plate with Centered Hole
```json
{
"parts": [{
"name": "plate",
"primitive": {"type": "cube", "size": {"x": 50, "y": 50, "z": 5}},
"operations": [
{"type": "hole", "diameter": 6, "at": "center"}
]
}]
}
```
### Plate with Corner Holes
```json
{
"parts": [{
"name": "mounting_plate",
"primitive": {"type": "cube", "size": {"x": 100, "y": 60, "z": 5}},
"operations": [
{"type": "hole", "diameter": 4, "at": {"x": 10, "y": 10}},
{"type": "hole", "diameter": 4, "at": {"x": 90, "y": 10}},
{"type": "hole", "diameter": 4, "at": {"x": 10, "y": 50}},
{"type": "hole", "diameter": 4, "at": {"x": 90, "y": 50}}
]
}]
}
```
### Cylinder with Blind Hole
```json
{
"parts": [{
"name": "bushing",
"primitive": {"type": "cylinder", "radius": 15, "height": 20},
"operations": [
{"type": "hole", "diameter": 10, "depth": 15, "at": "center"}
]
}]
}
```
### L-Bracket
```json
{
"parts": [{
"name": "bracket",
"primitive": {"type": "cube", "size": {"x": 40, "y": 40, "z": 5}},
"operations": [
{"type": "union", "primitive": {"type": "cube", "size": {"x": 5, "y": 40, "z": 30}}, "at": {"x": 0, "y": 0, "z": 5}},
{"type": "hole", "diameter": 5, "at": {"x": 20, "y": 20}},
{"type": "difference", "primitive": {"type": "cylinder", "radius": 2.5, "height": 40}, "at": {"x": 2.5, "y": 20, "z": 20}}
]
}]
}
```
### Linear Pattern of Holes
```json
{
"parts": [{
"name": "rail",
"primitive": {"type": "cube", "size": {"x": 200, "y": 20, "z": 10}},
"operations": [
{
"type": "difference",
"primitive": {"type": "cylinder", "radius": 3, "height": 15},
"at": {"x": 20, "y": 10, "z": -2}
},
{
"type": "linear_pattern",
"direction": {"x": 1, "y": 0, "z": 0},
"count": 5,
"spacing": 40
}
]
}]
}
```
### Circular Pattern
```json
{
"parts": [{
"name": "flange",
"primitive": {"type": "cylinder", "radius": 40, "height": 10},
"operations": [
{"type": "hole", "diameter": 20, "at": "center"},
{
"type": "difference",
"primitive": {"type": "cylinder", "radius": 4, "height": 15},
"at": {"x": 30, "y": 0, "z": -2}
},
{
"type": "circular_pattern",
"axis_origin": {"x": 0, "y": 0, "z": 0},
"axis_dir": {"x": 0, "y": 0, "z": 1},
"count": 6,
"angle_deg": 360
}
]
}]
}
```
## Workflow
1. **Create**: Use `create_cad_document` to build geometry
2. **Inspect**: Use `inspect_cad` to verify dimensions and volume
3. **Export**: Use `export_cad` to save as `.stl` or `.glb`
## Tips
- Holes default to through-holes; specify `depth` for blind holes
- Use percentage positioning for parametric designs that scale
- Cube origin is at corner - add half-size to center operations
- Cylinder/cone origins are at base center - no X/Y offset needed for centered holes
- Always extend cutting cylinders past the part (the hole operation does this automatically)
## Setup
**Recommended:** Install the vcad Claude Code plugin for zero-config setup (includes MCP server, skills, and slash commands):
```bash
claude plugin add vcad
```
**Manual setup:** Add the vcad MCP server to your Claude Code config:
```json
{
"mcpServers": {
"vcad": {
"command": "npx",
"args": ["-y", "@vcad/mcp"]
}
}
}
```
Or run from local checkout:
```json
{
"mcpServers": {
"vcad": {
"command": "node",
"args": ["packages/mcp/dist/index.js"]
}
}
}
```Related Skills
vcad-step-import
Import and work with STEP files using vcad MCP tools. Use when the user mentions STEP files, .step, .stp, importing CAD from other software (Fusion 360, SolidWorks, Onshape), or converting between CAD formats.
vcad-assembly
Build multi-part assemblies with joints and run physics simulations. Use when the user asks about robot arms, mechanisms, hinges, joints, physics simulation, reinforcement learning environments, or assembly of multiple parts.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
repo-scan
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
project-flow-ops
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
product-lens
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
openclaw-persona-forge
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡, 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill,可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于:微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词:龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。