{
  "skill_name": "data-cleaning",
  "should_trigger": [
    "Audit this CSV before I use it for reporting.",
    "Design a reusable pipeline to clean and validate incoming JSON records.",
    "Why did this join multiply my rows, and how do I make the cleaning reproducible?"
  ],
  "should_not_trigger": [
    "Choose a statistical test for this experiment.",
    "Tune my XGBoost model's hyperparameters."
  ]
}