Skip to content
SkillModel-led434 tokens in use

brainstorm-ideas-new

Brainstorms feature ideas for a new product in initial discovery from PM, Designer and Engineer views, then ranks the top five.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-product-discovery/skills/brainstorm-ideas-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-ideas-new costs

49tokens idle
434tokens 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
  • Output10/15
  • 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-ideas-new supports initial product discovery, where the question is whether a new product should exist. The agent confirms the concept, target segment and what users want to achieve, then generates five specific feature ideas each from a product manager, a designer and an engineer.

It ranks the top five with extra weight on core value delivery, speed to validate and differentiation, and gives reasoning and assumptions to test for each.

What You Get

  • Fifteen specific feature ideas, five each from PM, Designer and Engineer perspectives
  • A ranked top five weighted toward core value and speed to validate
  • Reasoning for each prioritized idea
  • Key assumptions to test for each idea
  • A markdown document when the output is substantial

Common Use Cases

  • Exploring features for a startup idea before committing to a build
  • Generating options after a market research or competitive analysis pass
  • Getting onboarding, integration and platform ideas for a new product
  • Preparing candidate features for pretotype experiments

What Makes It Unique

The ranking leans on three criteria suited to a product that does not exist yet: does it solve the primary problem, can it be tested quickly and can it differ from alternatives. The three roles each have a new-product lens: market fit for the PM, onboarding and engagement for the designer, technical innovation and API integrations for the engineer. The brainstorm-ideas-existing skill covers continuous discovery for a live product.

Under The Hood

A single SKILL.md of instructions with no scripts. The agent reads market research files you attach with its own file tools and may use web search to understand the market. The skill says to save substantial output as a markdown document, so it can write a file. It does not tell the agent to 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