Brainstorm Experiments ExistingSAFE

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
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:

1. **Clarify the idea and assumptions**: Confirm what the team wants to build and what they need to validate.

2. **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)

3. **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

4. **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

- [Testing Product Ideas: The Ultimate Validation Experiments Library](https://www.productcompass.pm/p/the-ultimate-experiments-library)
- [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas)
- [What Is Product Discovery? The Ultimate Guide Step-by-Step](https://www.productcompass.pm/p/what-exactly-is-product-discovery)
- [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.