brainstorm-experiments-existing
phuryn/pm-skills
Design low-effort experiments to validate product assumptions before full implementation.
What is brainstorm-experiments-existing?
This skill helps product teams design experiments for existing products to test feature ideas and assumptions cheaply. Use it when you need to validate assumptions, test feature ideas with minimal effort, or plan product experiments before committing to full development.
- Clarify feature ideas and underlying assumptions that need validation
- Suggest appropriate experiment methods (prototypes, A/B tests, fake door tests, spikes, Wizard of Oz, surveys)
- Design experiments that measure actual user behavior rather than opinions
- Specify assumptions, experiment design, metrics, and success thresholds for each test
- Recommend risk mitigation strategies for production experiments
How to install brainstorm-experiments-existing
npx skills add https://github.com/phuryn/pm-skills --skill brainstorm-experiments-existingHow to use brainstorm-experiments-existing
- 1.Describe your feature idea and list the key assumptions you need to validate
- 2.Provide any supporting materials (PRDs, designs, assumption lists) if available
- 3.Work through the clarification step to confirm what needs testing
- 4.Review suggested experiment methods and select appropriate ones for your assumptions
- 5.For each experiment, define the assumption, specific test design, metric to measure, and success threshold
- 6.For production tests, identify and implement risk mitigation strategies
Use cases
- Validating whether users will actually use a proposed feature before building it
- Testing a new product direction with a fake door or feature stub
- Running an A/B test on production to measure feature adoption with risk controls
- Conducting a technical spike to validate feasibility assumptions
- Using first-click testing to validate navigation or interaction assumptions
- Product managers planning feature validation
- Product teams designing experiments
- Teams with feature ideas needing low-cost validation before commitment
brainstorm-experiments-existing FAQ
This skill focuses on low-effort, rapid experiments to validate specific assumptions before committing resources. It emphasizes behavioral measurement over opinions and aims for maximum learning with minimal effort.
Yes, but the skill emphasizes measuring actual behavior and includes guidance on risk mitigation strategies to protect users and the business when testing in production.
Always measure actual behavior. The skill explicitly recommends behavioral validation (task completion, feature adoption, clicks) over opinion-based surveys.
The skill suggests multiple methods beyond prototypes, including fake door tests, feature stubs, technical spikes, and Wizard of Oz approaches that require minimal upfront effort.
Full instructions (SKILL.md)
Source of truth, from phuryn/pm-skills.
name: brainstorm-experiments-existing description: "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."
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:
-
Clarify the idea and assumptions: Confirm what the team wants to build and what they need to validate.
-
Suggest experiments for each assumption. Consider methods like:
- First-click testing or task completion with a prototype
- Feature stubs or fake door tests
- Technical spikes
- A/B tests on production (with risk mitigation)
- Wizard of Oz approaches
- Survey-based validation (behavioral, not opinion-based)
-
Key principles to follow:
- Measure actual behavior, not users' opinions
- Test responsibly — don't put users or the business at risk
- For production tests (e.g., A/B tests), explain risk mitigation strategies
- Aim for maximum validated learning with minimal effort
-
For each experiment, specify:
- Assumption: What do we believe?
- Experiment: What exactly will we do to validate it?
- Metric: What will be measured?
- 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
Related skills
More from phuryn/pm-skills and the wider catalog.
brainstorm-experiments-new
Design lean startup experiments and XYZ hypotheses to validate new product ideas with minimal effort.
brainstorm-ideas-existing
Multi-perspective ideation for existing products using PM, Designer, and Engineer viewpoints.
brainstorm-ideas-new
Generate feature ideas for new products from PM, Designer, and Engineer perspectives.
brainstorm-okrs
Generate three ambitious, measurable OKR sets aligned with company strategy for quarterly planning.
business-model
Generate a Business Model Canvas with all 9 building blocks to map how a business creates, delivers, and captures value.
cohort-analysis
Analyze user retention, feature adoption, and engagement trends by cohort to identify churn patterns and behavioral insights.