‹ 首页

brainstorm-experiments-existing

@phuryn · 收录于 1 周前 · 上游提交 1 周前★ 社区精选

Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods. Use when validating assumptions, testing feature ideas cheaply, or planning product experiments.

适合你,如果正在为现有产品设计验证实验

/ 通过 npx 安装 校验哈希
npx oh-my-skill add phuryn/pm-skills/brainstorm-experiments-existing
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- phuryn/pm-skills/brainstorm-experiments-existing
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify phuryn/pm-skills/brainstorm-experiments-existing
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
23265GitHub stars
~483上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 18468a9 · 表述以原文为准
它做什么

当用户描述一个现有产品的功能想法和假设时,Claude 会设计低成本的实验来验证这些假设,例如原型测试、A/B 测试、技术探针等,并给出每个实验的假设、具体做法、衡量指标和成功标准。

什么时候触发

当用户需要验证现有产品的某个功能假设,或想低成本测试新想法时触发。用户需提供想法和假设,也可附上 PRD 或假设列表等文件。

装好后可以这样说
Claude 会设计实验来测试该功能假设。
Claude 会给出实验方案,包括指标和成功标准。
技能原文 SKILL.md作者撰写 · MIT · 18468a9
Design Experiments (Existing Product)

Design low-effort experiments to test product assumptions before committing to full implementation.

Context

You are helping a product team design experiments for $ARGUMENTS. The team has a feature idea and assumptions that need validation.

If the user provides files (PRDs, assumption lists, designs), read them first.

Instructions

The user will describe their idea and assumptions. Work through these steps:

  1. Clarify the idea and assumptions: Confirm what the team wants to build and what they need to validate.
  1. Suggest experiments for each assumption. Consider methods like:
  2. First-click testing or task completion with a prototype
  3. Feature stubs or fake door tests
  4. Technical spikes
  5. A/B tests on production (with risk mitigation)
  6. Wizard of Oz approaches
  7. Survey-based validation (behavioral, not opinion-based)
  1. Key principles to follow:
  2. Measure actual behavior, not users' opinions
  3. Test responsibly — don't put users or the business at risk
  4. For production tests (e.g., A/B tests), explain risk mitigation strategies
  5. Aim for maximum validated learning with minimal effort
  1. For each experiment, specify:
  2. Assumption: What do we believe?
  3. Experiment: What exactly will we do to validate it?
  4. Metric: What will be measured?
  5. Success threshold: The expected value if we are right

Think step by step. Present experiments in a clear table or structured format. Save as markdown if substantial.


Further Reading
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。