sensitivity-analyzer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited sensitivity-analyzer (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
The Sensitivity Analyzer skill provides comprehensive capabilities for identifying critical inputs and understanding how model outputs respond to parameter changes. It supports both local (one-at-a-time) and global sensitivity analysis methods, enabling robust decision-making under uncertainty.
# Define OAT analysis
oat_config = {
"base_case": {
"price": 100,
"volume": 10000,
"cost": 60,
"fixed_costs": 200000
},
"variations": {
"price": {"range": [-20, 20], "step": 5, "unit": "%"},
"volume": {"range": [-30, 30], "step": 10, "unit": "%"},
"cost": {"range": [-15, 15], "step": 5, "unit": "%"},
"fixed_costs": {"range": [-10, 10], "step": 5, "unit": "%"}
},
"output_variable": "profit"
}# Define Sobol analysis
sobol_config = {
"parameters": {
"price": {"bounds": [80, 120], "distribution": "uniform"},
"volume": {"bounds": [7000, 13000], "distribution": "uniform"},
"cost": {"bounds": [50, 70], "distribution": "uniform"}
},
"sample_size": 10000,
"calculate_second_order": True
}Efficient screening method for many parameters:
| Index | Meaning |
|---|---|
| S1 (First-order) | Direct effect of parameter |
| ST (Total) | Direct + all interaction effects |
| S2 (Second-order) | Pairwise interaction effect |
{
"analysis_type": "OAT|sobol|morris|breakeven",
"model": "function or expression",
"parameters": {
"param_name": {
"base_value": "number",
"range": ["number", "number"],
"distribution": "string"
}
},
"options": {
"sample_size": "number",
"output_variable": "string",
"calculate_interactions": "boolean",
"confidence_level": "number"
}
}{
"analysis_type": "string",
"parameter_rankings": [
{
"parameter": "string",
"importance_score": "number",
"effect_direction": "positive|negative",
"first_order_index": "number",
"total_index": "number"
}
],
"breakeven_points": {
"parameter": {
"breakeven_value": "number",
"current_distance": "number"
}
},
"interactions": [
{
"parameters": ["string", "string"],
"interaction_index": "number"
}
],
"tornado_data": {
"parameter": {
"low_output": "number",
"high_output": "number",
"swing": "number"
}
},
"visualization_paths": ["string"]
}Identifies the parameter value where:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.