{"slug":"foryourhealth111-pixel-evaluating-machine-learning-models","source_name":"foryourhealth111-pixel/evaluating-machine-learning-models","name":"Foryourhealth111 Pixel/Evaluating Machine Learning Models","description":"Evaluate trained machine learning models with the right metrics and comparison logic.\nUse for benchmark review, threshold selection, calibration, validation, and model comparison; not for feature engineering or leakage auditing.","version":1,"lift":{"pass_rate_delta_pts":-100,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":15.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-13T21:03:37.466437+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":-100,"with_pass_pct":0,"without_pass_pct":100,"tokens_delta_pct":15.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-13T21:03:37.466437+00:00","run_id":"4e4f7635-b523-410b-b886-7f651cf22fca","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"ce062ebe40416239e91f6a64ba97d07a7d15dc45a5152f41a0c2962f128a6f12","raw_url":"https://app.decimal.ai/s/foryourhealth111-pixel-evaluating-machine-learning-models/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/foryourhealth111-pixel-evaluating-machine-learning-models"}