{"slug":"jeremylongshore-hypothesis-tester","source_name":"jeremylongshore/hypothesis-tester","name":"Jeremylongshore/Hypothesis Tester","description":"Structured hypothesis formulation, experiment design, and results interpretation for Product Managers. Use when the user needs to validate an assumption, design an A/B test, evaluate experiment results, or decide whether to ship based on data. Triggers include \"hypothesis\", \"A/B test\", \"experiment\", \"validate assumption\", \"test this\", \"should we ship\", or when making a decision that should be data-informed.","version":1,"lift":{"pass_rate_delta_pts":8.7,"pass_rate_pct":82.6,"total_cases":23,"passed_cases":19,"tokens_delta_pct":97.8,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-30T18:34:50.365292+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":8.7,"with_pass_pct":82.6,"without_pass_pct":73.9,"tokens_delta_pct":97.8,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":23,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-30T18:34:50.365292+00:00","run_id":"d99e8498-7579-41d1-a409-aa8d18df4de7","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":"588982c252f8363f40d08b0466cafd6ca9abb260095c8c7e2649b04079a1dc07","raw_url":"https://app.decimal.ai/s/jeremylongshore-hypothesis-tester/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/jeremylongshore-hypothesis-tester"}