Brainstorm Experiments Existing
Plan cheap, behavior-measuring experiments to test assumptions on an existing product before full feature builds.
Overview
brainstorm-experiments-existing is an agent skill most often used in Validate (also Grow, Ship) that designs low-effort experiments to test product assumptions on an existing offering.
Install
npx skills add https://github.com/phuryn/pm-skills --skill brainstorm-experiments-existingWhat is this skill?
- Clarifies the feature idea and assumptions from user input or uploaded PRDs
- Maps each assumption to experiments: prototypes, fake doors, spikes, A/B tests, surveys
- Emphasizes measuring actual behavior—not opinion surveys
- Includes risk mitigation guidance for production A/B tests
- Optimizes for maximum validated learning with minimal effort
- 6+ experiment method families referenced (prototype tests, fake doors, spikes, A/B, wizard of Oz, behavioral surveys)
Adoption & trust: 1k installs on skills.sh; 12.3k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a live product and a new feature idea, but you do not know which assumptions are false—and full implementation feels too expensive to gamble on.
Who is it for?
Solo PM-founder types validating feature bets on an existing SaaS or app with time-boxed spikes, prototypes, or guarded A/B tests.
Skip if: Greenfield ideas with no users yet (use discovery-style brainstorming instead), or teams that already have a locked experiment backlog and only need tooling execution.
When should I use this skill?
Validating assumptions, testing feature ideas cheaply, or planning product experiments on an existing product.
What do I get? / Deliverables
A structured set of behavior-focused experiments per assumption, with risk-aware options for production tests, ready to run before you commit build capacity.
- Per-assumption experiment recommendations
- Risk mitigation notes for production tests
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Validate because the skill targets assumption testing and low-effort learning before committing implementation on a live product. Prototype subphase fits prototypes, spikes, fake doors, and wizard-of-oz flows that de-risk ideas without shipping full features.
Where it fits
Turn a pricing-page assumption into a clickable prototype and first-click test before engineering checkout changes.
List must-be-true assumptions from a PRD and attach the cheapest spike or fake door per line.
Design a limited rollout A/B with guardrails before exposing a risky UX change to all production users.
Frame an engagement hypothesis as a measurable experiment instead of a vanity metric dashboard tweak.
How it compares
Use instead of jumping from PRD to sprint planning without a cheap validation layer for each assumption.
Common Questions / FAQ
Who is brainstorm-experiments-existing for?
Product-minded solo builders and small teams shipping iterative improvements who need experiment designs tied to explicit assumptions.
When should I use brainstorm-experiments-existing?
In Validate when scoping a feature on an existing product; in Ship when planning a guarded production A/B; in Grow when testing lifecycle or engagement hypotheses with measured behavior.
Is brainstorm-experiments-existing safe to install?
It only guides experiment design; review the Security Audits panel on this page and apply your own governance before running production tests on real users.
SKILL.md
READMESKILL.md - Brainstorm Experiments Existing
## 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)