library/specializations/domains/science/mechanical-engineering/skills/test-planning/SKILL.md
Skill for comprehensive mechanical test plan development and execution support
npx skillsauth add a5c-ai/babysitter test-planningInstall 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 Test Plan Development skill provides comprehensive capabilities for developing mechanical test plans including objective definition, test configuration, instrumentation planning, and data analysis procedures.
Verification vs Validation | Type | Question | Purpose | |------|----------|---------| | Verification | Built correctly? | Meets specifications | | Validation | Built the right thing? | Meets user needs |
Test Categories
Success Criteria
Pass/Fail criteria must be:
- Measurable and quantitative
- Traceable to requirements
- Unambiguous
- Defined before testing
Configuration Control
Pre-Test Condition
Boundary Conditions
Fixture requirements:
- Simulate actual mounting
- Minimize artificial constraints
- Allow access for instrumentation
- Safe for failure modes
Load Introduction
| Type | Application | Accuracy | |------|-------------|----------| | Foil gage | General purpose | +/- 1% | | Rosette | Unknown principal direction | +/- 1% | | Clip gage | Large strains | +/- 0.5% | | DIC | Full-field | +/- 2% |
| Type | Range | Accuracy | |------|-------|----------| | LVDT | +/- 50 mm | +/- 0.1% | | String pot | 0-2000 mm | +/- 0.5% | | Laser | 0-500 mm | +/- 0.01% | | Dial indicator | 0-50 mm | +/- 0.02 mm |
Load cell selection:
- Capacity: 1.5-2x expected maximum
- Accuracy: Class 0.1 or better for critical
- Type: Tension, compression, universal
- Environmental: Temperature, humidity range
| Type | Range | Bandwidth | |------|-------|-----------| | Piezoelectric | +/- 500 g | 1 Hz - 10 kHz | | MEMS | +/- 50 g | DC - 1 kHz | | Capacitive | +/- 10 g | DC - 100 Hz |
Nyquist criterion: f_sample >= 2 * f_max
Practical guideline: f_sample >= 5-10 * f_max
For transient events:
- Sample at 10x highest frequency content
- Include anti-aliasing filter
Channel List
Data Management
1. Scope and applicability
2. Reference documents
3. Safety requirements
4. Equipment and materials
5. Pre-test setup
6. Test execution steps
7. Data recording requirements
8. Post-test procedures
9. Acceptance criteria
10. Reporting requirements
Hazard Analysis
Risk Mitigation
| Data Type | Analysis Method | Output | |-----------|-----------------|--------| | Static load-displacement | Linear regression | Stiffness | | Stress-strain | Offset method | Yield strength | | Fatigue | S-N curve fit | Life equation | | Vibration | FFT, modal fit | Frequencies, damping |
Combined uncertainty:
u_c = sqrt(sum(u_i^2))
Expanded uncertainty (95%):
U = k * u_c (k = 2 for 95%)
Sources:
- Calibration uncertainty
- Resolution
- Environmental effects
- Repeatability
{
"test_article": {
"part_number": "string",
"description": "string",
"quantity": "number"
},
"requirements": {
"specifications": "array of requirement IDs",
"success_criteria": "array"
},
"test_type": "development|qualification|acceptance|certification",
"test_conditions": {
"loads": "array of load cases",
"environments": "array of conditions",
"duration": "string"
},
"resources": {
"facility": "string",
"equipment": "array",
"personnel": "array"
}
}
{
"test_plan": {
"document_number": "string",
"revision": "string",
"test_matrix": "array of test cases",
"instrumentation_list": "array",
"schedule": "object"
},
"test_procedures": "array of procedure references",
"safety_analysis": {
"hazards": "array",
"controls": "array",
"approval_required": "boolean"
},
"data_analysis_plan": {
"methods": "array",
"acceptance_criteria": "array"
},
"resource_requirements": {
"cost_estimate": "number",
"duration": "number (days)",
"personnel": "array"
}
}
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.