What problem does it solve? Founders often run growth experiments ad hoc, without clear hypotheses, budget allocation, or criteria for when to stop or scale, wasting cash and producing unreliable learning. This Skill structures growth experimentation as a managed portfolio with explicit economics, guardrails, and evidence-based decision rules. ## Core Features & Use Cases - Hypothesis-Driven Experiment Design: Generates hypotheses, scores evidence and upside, and designs minimum viable tests before committing resources. - Budget Allocation & Stop/Scale Rules: Allocates test budgets across experiments and applies sequential rules for stopping, scaling, or escalating based on leading indicators. - Risk-Adjusted Decision Framework: Ranks options by constraint compliance, confidence-weighted value, time-to-value, and reversibility, with human approval gates for material commitments. - Use Case: A founder wants to improve customer acquisition without exceeding cash limits. The Skill compares at least three feasible experiment options against the counterfactual, recommends the highest confidence-weighted option that passes all hard constraints, and sets up monitoring with stop and scale conditions. ## Quick Start Ask the agent to build a growth experiment portfolio for your company that improves a target metric within your cash, risk, and capacity constraints.
