Skip to content
SkillModel-led503 tokens in use

brainstorm-experiments-new

Writes an XYZ hypothesis for a new product and designs two or three pretotype experiments such as landing pages and pre-orders.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-product-discovery/skills/brainstorm-experiments-new
claude plugin marketplace add phuryn/pm-skills claude plugin install pm-product-discovery@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing brainstorm-experiments-new costs

58tokens idle
503tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples0/15
  • Output7/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

brainstorm-experiments-new applies lean startup methodology to a new product concept. The agent first writes an XYZ hypothesis in the form “At least X% of Y will do Z”, then proposes two or three pretotype experiments to test it with minimal effort.

Options include a landing page, explainer video, email campaign, pre-order or waitlist and a concierge or manual MVP. The method follows Alberto Savoia’s The Right It, favoring skin in the game and your own data over other people’s data.

What You Get

  • An XYZ hypothesis with the percentage, target market and action filled in
  • Two or three pretotype experiments chosen for low effort
  • A method, metric and success threshold for each experiment
  • Guidance to test willingness to pay with real commitment

Common Use Cases

  • Testing demand for a startup idea with a landing page and sign-up goal
  • Designing a pre-order or waitlist test to check willingness to pay
  • Running a concierge MVP before writing any code
  • Turning a vague concept into a measurable hypothesis

What Makes It Unique

The skill is built on Alberto Savoia’s pretotyping ideas: skin in the game, which treats real commitment of time, money or reputation as the reliable signal, and Your Own Data (YODA), which prefers data you collect over market reports or analogies. The XYZ hypothesis format makes the target measurable from the start. The existing-product counterpart, brainstorm-experiments-existing, covers prototypes, fake doors and A/B tests on a live product.

Under The Hood

A single SKILL.md of instructions with no scripts. The agent reads any market research or mockup files you attach with its own file tools and writes the hypothesis and experiments in the conversation. The skill says to save substantial output as markdown, so it can write a file. It does not tell the agent to fetch web pages, call APIs or run commands. Your concept replaces $ARGUMENTS in the prompt.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers