library/specializations/domains/science/mechanical-engineering/skills/additive-manufacturing/SKILL.md
Skill for additive manufacturing process selection, design optimization, and build preparation
npx skillsauth add a5c-ai/babysitter additive-manufacturingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The Additive Manufacturing skill provides capabilities for AM process selection, design optimization, and build preparation, enabling effective use of additive technologies for prototyping and production applications.
| Process | Materials | Resolution | Applications | |---------|-----------|------------|--------------| | DMLS/SLM | Ti, Al, Steel, Inconel | 30-50 um layer | Aerospace, medical | | EBM | Ti, CoCr | 50-100 um layer | Orthopedic implants | | DED | Most metals | 250+ um | Large parts, repair | | Binder Jet | Steel, bronze | 80-100 um | Tooling, high volume |
| Process | Materials | Resolution | Applications | |---------|-----------|------------|--------------| | SLS | Nylon, TPU | 100-150 um | Functional prototypes | | SLA/DLP | Photopolymers | 25-100 um | High detail, patterns | | FDM | ABS, PLA, PC, PEEK | 100-300 um | Prototypes, tooling | | MJF | Nylon | 80 um | Production parts |
Minimum self-supporting angle:
- Metal (DMLS): 45 degrees from horizontal
- Polymer (SLS): 0 degrees (self-supporting)
- FDM: 45 degrees (with support)
- SLA: 30-45 degrees
Overhang rule:
- Unsupported distance < 2 mm (metal)
- Unsupported distance < 5 mm (polymer)
| Process | Min Wall | Min Hole | Min Detail | |---------|----------|----------|------------| | DMLS | 0.4 mm | 0.5 mm | 0.2 mm | | SLS | 0.7 mm | 1.0 mm | 0.3 mm | | SLA | 0.5 mm | 0.5 mm | 0.1 mm | | FDM | 0.8 mm | 2.0 mm | 0.5 mm |
Topology Optimization
Lattice Structures | Type | Relative Density | Application | |------|-----------------|-------------| | Octet truss | 10-40% | High stiffness | | Diamond | 15-35% | Isotropic | | Gyroid | 10-50% | Bone ingrowth | | Honeycomb | 20-50% | Directional load |
Part Consolidation
Optimization criteria:
1. Minimize support volume
2. Optimize surface finish on critical surfaces
3. Reduce build height (time)
4. Ensure feature accuracy
Trade-off example:
- Flat orientation: Less support, rougher top surface
- Angled orientation: More support, better detail
Support Types | Type | Application | Removal | |------|-------------|---------| | Block | Large overhangs | Manual/machining | | Tree | Complex geometry | Manual | | Lattice | Heat dissipation | Manual | | Cone | Point supports | Manual |
Support Minimization
Minimum spacing:
- DMLS: 2-5 mm between parts
- SLS: 2-3 mm (powder acts as support)
- FDM: N/A (single part builds)
- SLA: 2-3 mm
Packing efficiency target: 5-15% of build volume
Required
Optional
SLS/MJF
SLA/DLP
{
"part_model": "CAD file reference",
"material_requirement": {
"type": "metal|polymer",
"specific": "string (e.g., Ti6Al4V, Nylon 12)",
"properties": "strength|stiffness|temperature|biocompatible"
},
"quantity": "number",
"quality_requirements": {
"tolerance": "number (mm)",
"surface_finish": "string",
"critical_features": "array"
},
"timeline": "prototype|production",
"budget_constraint": "number (optional)"
}
{
"process_recommendation": {
"technology": "string",
"material": "string",
"machine": "string (if specific)"
},
"build_preparation": {
"orientation": "description and rationale",
"support_volume": "number (cm3)",
"build_time": "number (hours)",
"material_usage": "number (kg)"
},
"dfam_recommendations": [
{
"feature": "string",
"issue": "string",
"recommendation": "string"
}
],
"post_processing": "array of steps",
"cost_estimate": {
"material": "number",
"machine_time": "number",
"post_processing": "number",
"total": "number"
}
}
development
Model documentation skill for generating model cards following Google's model card framework.
development
MLflow integration skill for experiment tracking, model registry, and artifact management. Enables LLMs to log experiments, compare runs, manage model lifecycle, and retrieve artifacts through the MLflow API.
data-ai
LIME-based local explanation skill for individual predictions across tabular, text, and image data.
devops
Kubeflow Pipelines skill for ML workflow orchestration, component management, and Kubernetes-native ML.