{"slug":"hashgraph-online-ml-experiment-evaluation","source_name":"hashgraph-online/ml-experiment-evaluation","name":"Hashgraph Online/ML Experiment Evaluation","description":"Plan evaluation strategies for machine-learning product changes. Use when deciding between offline evaluation, interleaving, online A/B tests, multi-armed bandits, or model filtering for ranking, recommendation, search, personalization, or other ML-powered user experiences.","version":1,"lift":{"pass_rate_delta_pts":8.33,"pass_rate_pct":95.8,"total_cases":24,"passed_cases":23,"tokens_delta_pct":-3.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-16T04:05:28.757455+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":8.33,"with_pass_pct":95.8,"without_pass_pct":87.5,"tokens_delta_pct":-3.9,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":24,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-16T04:05:28.757455+00:00","run_id":"fe455539-19df-4ec1-84e9-ef89b8a94672","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":"80bd79cf927e8a561bcb63370cb54ab147e44ce367cc84f07f9f9f248609d72c","raw_url":"https://app.decimal.ai/s/hashgraph-online-ml-experiment-evaluation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/hashgraph-online-ml-experiment-evaluation"}