优先级假设（prioritize-assumptions）
2026-10-22查看 1复制 0
使用“影响 × 风险”矩阵和实验为假设排序。
📘如何使用这个技能
- 1复制技能内容·点击上方「Copy SKILL.md」复制全部内容，或 Download 下载到本地
- 2打开你的 AI 客户端·支持 Claude Code、Trae、Cursor、ChatGPT、DeepSeek、Kimi 等任意 AI 助手
- 3粘贴为系统提示/知识文件·Claude Code：放入 .claude/skills/ 目录；普通对话：作为首条消息发送并说「请严格按这份技能文档执行」
- 4直接提出你的需求·AI 会按技能定义的工作流、格式和约束来处理，无需再解释背景
💡 提示：技能生效后，每次对话只需一句需求，AI 会按 SKILL.md 的流程执行。
SKILL.md2283 chars
--- 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)