← ClaudeAtlas

hypothesis-generate-assumptionslisted

Generate exactly one hypothesis candidate by enumerating and combining testable assumptions.
panjose/Co-Scientist · ★ 4 · AI & Automation · score 77
Install: claude install-skill panjose/Co-Scientist
# hypothesis-generate-assumptions Goal: - Generate exactly one hypothesis candidate by enumerating and combining testable assumptions. Inputs: - `research_plan/RESEARCH_PLAN.json` - `state/STRATEGY_PLAN.json` - optional parent hypothesis and review artifacts when the round is part of an evolution continuation Outputs: - `hypotheses/<id>/HYPOTHESIS.json` - `hypotheses/<id>/HYPOTHESIS.md` - `hypotheses/<id>/ORIGIN.json` Context Loading: - Read `research_plan/RESEARCH_PLAN.json`. - Use `research_goal` as the objective that the assumption chain must explain or enable. - Use `preferences` as quality criteria. - Use `constraints` as hard boundaries. - Read `state/STRATEGY_PLAN.json` and confirm that the current round allows `assumptions_identification_generation`. - If the round is parented, read the selected parent hypothesis and its latest review summary before proposing a child. The new chain should address known weaknesses where possible. Execution Prompt Contract: - System Intent: - You are generating one candidate hypothesis by surfacing the smallest useful chain of testable assumptions. - Required Reasoning Focus: - Identify 3-5 assumptions or fewer if a shorter chain is stronger. - Favor chains that are falsifiable, mechanistically informative, and non-trivial. - At least one link may be speculative, but it must remain testable and explicit. - Use the assumption chain to produce a full downstream hypothesis rather than stopping at the decomposition. - Do