先看看示例
作者提供的示例，实际效果取决于你的输入和使用工具。
输入
A：用户愿上传经营数据，无证据，失败则产品不可用。B：用户喜欢深色界面，有2人提到，不影响核心使用。
输出
编辑示例 · 未运行
| 顺序 | 假设 | 理由 | 最小验证 |
|---|---|---|---|
| 1 | 愿上传经营数据 | 影响核心价值且缺证据 | 访谈并观察一次脱敏样表导入 |
| 2 | 喜欢深色界面 | 影响较低，已有少量偏好线索 | 在原型比较两种主题 |
方法说明
--- name: prioritize-assumptions description: "Prioritize assumptions using an Impact × Risk matrix and suggest experiments for each. Use when triaging a list of assumptions, deciding what to test first, or applying the assumption prioritization canvas." --- ## Prioritize Assumptions Triage assumptions using an Impact × Risk matrix and suggest targeted experiments. ### Context You are helping prioritize assumptions for **$ARGUMENTS**. If the user provides files with assumptions or research data, read them first. ### Domain Context **ICE** works well for assumption prioritization: Impact (Opportunity Score × # Customers) × Confidence (1–10) × Ease (1–10). Opportunity Score = Importance × (1 − Satisfaction), normalized to 0–1 (Dan Olsen). **RICE** splits Impact into Reach × Impact separately: (R × I × C) / E. See the `prioritization-frameworks` skill for full formulas and templates. ### Instructions The user will provide a list of assumptions to prioritize. Apply the following framework: 1. **For each assumption**, evaluate two dimensions: - **Impact**: The value created by validating this assumption AND the number of customers affected (in ICE: Impact = Opportunity Score × # Customers) - **Risk**: Defined as (1 - Confidence) × Effort 2. **Categorize each assumption** using the Impact × Risk matrix: - **Low Impact, Low Risk** → Defer testing until higher-priority assumptions are addressed - **High Impact, Low Risk** → Proceed to implementation (low risk, high reward) - **Low Impact, High Risk** → Reject the idea (not worth the investment) - **High Impact, High Risk** → Design an experiment to test it 3. **For each assumption requiring testing**, suggest an experiment that: - Maximizes validated learning with minimal effort - Measures actual behavior, not opinions - Has a clear success metric and threshold 4. **Present results** as a prioritized matrix or table. Think step by step. Save as markdown if the output is substantial. --- ### Further Reading - [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas) - [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)