Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

brainstorm-experiments-new — Claude Code skill: pretotype tests

Turns a new product idea into an XYZ hypothesis plus 2-3 pretotypes, each with a metric and a success threshold. Use it before writing code, to see whether anyone wants the thing.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add phuryn/pm-skills --skill brainstorm-experiments-new -a claude-code
Open on GitHub

What brainstorm-experiments-new does

The skill runs an idea through lean startup: first an XYZ hypothesis of the form a set share of a named audience will do a specific thing, then 2-3 pretotypes to test it. The options it reaches for are landing pages, explainer videos, email campaigns, pre-orders or waitlists, and a manual concierge MVP. Every experiment comes out with the hypothesis under test, the method, the metric and a success threshold, so the miss condition is clear before you spend anything.

The thinking follows Alberto Savoia's "The Right It": skin-in-the-game and YODA, your own data over other people's reports. A pile of email sign-ups won't earn much credit here, because the skill counts real commitment of time, money or reputation as the signal.

Pass the product concept in the request itself. Attached files get read first, market research or landing page mockups among them, and a long result is saved as markdown.

What it helps with

  • turn a rough product idea into an XYZ hypothesis
  • choose 2-3 pretotypes for one specific hypothesis
  • fix the metric and success threshold before the test runs
  • test willingness to pay instead of casual interest
  • collect first-hand data rather than market reports

Example prompts for the agent

  • Validate a new product idea: write the XYZ hypothesis and propose 2-3 pretotypes with metrics.
  • Read `market-research.md` and the landing mockup first, then build the hypothesis and experiments around them.
  • I need to test willingness to pay — which pretotype should I run and what threshold counts as success?

How to install brainstorm-experiments-new

1Skills CLI (Vercel)

npx skills add phuryn/pm-skills --skill brainstorm-experiments-new -a claude-code

2Manually: put the files in place

~/.claude/skills/brainstorm-experiments-new/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/brainstorm-experiments-new/

From the same set61

The whole set →
create-prd phuryn This skill builds a lean PRD from an 8-section template. Use it to define a feature, document product requirements, or review an existing PRD. Claude Code CX Codex Cursor +1 10,800installs pre-mortem phuryn Runs a pre-mortem risk assessment on PRDs and launch plans. Catches critical launch blockers, surfaces hidden team assumptions, and maps action items. Claude Code CX Codex Cursor +1 10,200installs outcome-roadmap phuryn Rewrites feature-heavy roadmaps into outcome-focused statements tied to business and customer impact. Helps teams replace rigid feature lists with measurable strategic goals. Claude Code CX Codex Cursor +1 9,900installs prioritization-frameworks phuryn Reference guide to 9 prioritization frameworks: RICE, ICE, Opportunity Score, Kano, MoSCoW and more. Helps you pick the right method, compare approaches, and rank tasks by importance. Claude Code CX Codex Cursor +1 9,900installs strategy-red-team phuryn Stress-tests PRDs, roadmaps, and strategies by attacking load-bearing assumptions before reality does, returning kill criteria and cheap tests. Claude Code CX Codex Cursor +1 9,200installs competitor-analysis phuryn This skill researches direct competitors and compares their positioning, strengths, weaknesses, and pricing. Use it to prepare a competitive brief or find ways to differentiate a product. Claude Code CX Codex Cursor +1 3,800installs business-model phuryn Skill generates a Business Model Canvas with all 9 building blocks: from key partners and activities to channels and revenue streams. Use it to create a business model, document how value flows, or analyze an existing business. Claude Code CX Codex Cursor +1 3,700installs privacy-policy phuryn Skill drafts a detailed privacy policy accounting for GDPR, CCPA, and other regulations. Use it when building a new product, updating data protection docs, or preparing for compliance audits. Claude Code CX Codex Cursor +1 3,500installs

Similar

reference-list-builder Paramchoudhary This skill structures professional reference lists and drafts briefing materials for employment background checks. Claude Code CX Codex Cursor +1 9,300installs offer-comparison-analyzer Paramchoudhary This skill compares job offers by total compensation, work conditions, career prospects, and risk. Use it when you are choosing between multiple offers. Claude Code CX Codex Cursor +1 9,300installs apple-notes Hermes Agent Lets a coding agent read, search and write Apple Notes from the terminal through the memo CLI, with everything syncing over iCloud. Claude Code CX Codex Cursor +1 381installs airtable community Ready-made curl calls for Airtable's REST API: read records, filter with formulas, write in batches, upsert on a merge field. Claude Code CX Codex Cursor +1 375installs find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs handoff Matt Pocock Creates a handoff document from the current conversation so another agent can continue the work. Use it when a task moves to a new session or agent. Claude Code 1,038,491installs

Questions about brainstorm-experiments-new

How do I install brainstorm-experiments-new in Claude Code?

One command: npx skills add phuryn/pm-skills --skill brainstorm-experiments-new -a claude-code. The skill file lands at ~/.claude/skills/brainstorm-experiments-new/SKILL.md.

What does brainstorm-experiments-new do?

It writes an XYZ hypothesis for a new product concept and suggests pretotype experiments to test it. Each experiment gets a method, a metric and a success threshold.

Does it work outside Claude Code?

Yes. The same skill installs for Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode; for Copilot the command is gh skill install phuryn/pm-skills brainstorm-experiments-new.

Source text

SKILL.md · MIT 
---
name: brainstorm-experiments-new
description: "Design lean startup experiments (pretotypes) for a new product. Creates XYZ hypotheses and suggests low-effort validation methods like landing pages, explainer videos, and pre-orders. Use when validating a new product idea, creating pretotypes, or testing market demand."
---

## Design Lean Startup Experiments (New Product)

Create XYZ hypotheses and design pretotype experiments to validate a new product concept with minimal effort.

### Context

You are helping validate a new product concept: **$ARGUMENTS** using lean startup methodology.

If the user provides files (market research, landing page mockups), read them first.

### Instructions

1. **Create an XYZ Hypothesis** in the form: "At least X% of Y will do Z"
   - **X%**: The percentage of the target market expected to engage
   - **Y**: The specific target market (e.g., "mid-size luxury sedan buyers")
   - **Z**: How they will engage with the product

2. **Suggest 2-3 pretotype experiments** to test the hypothesis with minimal effort. Consider:
   - **Landing Page**: Test interest by measuring sign-ups or clicks
   - **Explainer Video**: Test understanding and appeal through engagement metrics
   - **Email Campaign**: Test demand through response and click-through rates
   - **Pre-Order / Waitlist**: Test willingness to pay through skin-in-the-game commitment
   - **Concierge / Manual MVP**: Deliver the service manually to test value

3. **Key principles** (Alberto Savoia, *The Right It*):
   - **Skin-in-the-Game**: Test willingness to pay — not just interest. Real commitment (time, money, reputation) is the only reliable signal.
   - **Your Own Data (YODA)**: Collect your own data through experiments rather than relying on Others' Data (ODP) like market reports or analogies. "The market for your idea does not care about the market for someone else's idea."
   - Measure actual behavior, not users' opinions

4. **For each experiment**, specify the hypothesis being tested, the method, the metric, and the success threshold.

Think step by step. Save as markdown if substantial.

---

### Further Reading

- [How to Build the Right Product with Alberto Savoia (ex-Innovator at Google)](https://www.productcompass.pm/p/how-to-build-the-right-product-with)
- [Testing Product Ideas: The Ultimate Validation Experiments Library](https://www.productcompass.pm/p/the-ultimate-experiments-library)
- [Continuous Product Discovery Masterclass (CPDM)](https://www.productcompass.pm/p/cpdm) (video course)

© phuryn · MIT · phuryn/pm-skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor