← Back to list
🛠️

brainstorm-experiments-existing Checked

Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, a…
🛠️ Developer Tools skills By phuryn Version v1.0.0 Added 2026-09-03 Updated 2026-09-03 Source ↗
7.6Overall rating
2Views
4Downloads
26.0kStars

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "brainstorm-experiments-existing" skill by following the instructions at https://skill123.me/install/brainstorm-experiments-existing.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/brainstorm-experiments-existing.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 1 KB
📊 Static rating
7.6/10
Trigger
7.0
Structure
7.3
Workflow
6.4
Content
7.0
Engineering
9.0
Security
9.5

Six-dimension rubric with reviewer rationale.

View scorecard ↓
🛡 Dynamic test
—

Not live-tested yet — this skill is rated on static analysis only.

About this skill

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.

Documentation

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

Score breakdown

Trigger
7.0
Clear What/When with validation and experiment keywords; no When-Not boundary or phrasing variants.
Structure
7.3
Single compact file, clean sections, no redundancy; nothing offloaded to references.
Workflow
6.4
Task-oriented steps with a concrete experiment schema and risk-mitigation guardrail, but no failure handling or verification loop.
Content
7.0
Concise imperative instructions; output format instruction is slightly loose (table or structured format).
Engineering
9.0
Valid frontmatter, no scripts, no broken internal path references.
Security
9.5
No scripts or injection; all external links to reputable productcompass.pm.
Good experiment-design generator with per-experiment assumption/metric/threshold schema and responsible-testing guardrails, but no verification or error handling.