Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Systematically identify startup-worthy problems by leveraging your background, expertise, and network through structured interview scripts, market research, and validation planning.
npx claudepluginhub zhenya-vlasov/idea-finderShare bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.
Problem discovery, customer research, and opportunity identification for product managers.
Discovery & research skills: Discovery Interview Guide, Job Story Mapper, User Interview Synthesis, Assumption Mapper. Structure user research from screener to synthesis.
A local-first startup advisor that guides founders through idea validation, competitors research, hypotheses generation, MVP/prototype design, and more.
Product discovery skills for PMs: ideation, experiments, assumption testing, feature prioritization, and customer interview synthesis.
Structured thinking methods that counteract LLM reasoning biases during problem exploration — first principles, inversion, constraint manipulation, perspective forcing, analogy search, and more, with user-gated parallel subagent exploration for deep dives
A Claude Code skill that helps you systematically find the right problem to build a company around — before you commit your time and money.
Most founders don't fail because they can't build. They fail because they build something nobody needed badly enough to pay for.
The standard advice — "find a problem you're passionate about," "scratch your own itch," "talk to users" — is true but hollow. Passion is not signal. Your own itch might be a niche of one. "Talk to users" doesn't tell you how to talk to them, what questions to ask, or how to tell real pain from polite feedback.
What's missing is a structured process: a way to systematically map your whole world — your work, your hobbies, your relationships, your frustrations — and extract from it the problems that are narrow enough to solve, painful enough to pay for, and accessible enough to sell.
That's what this skill does.
⭐ Star this repo if you want Claude to research your ideas.
Idea Finder is a Claude Code skill that acts as a co-founder discovery agent. It interviews you about your life and expertise, researches every role you inhabit as a potential market, scores the opportunities it finds, and helps you validate the strongest ones before you commit.
It keeps a running discovery.md — your complete discovery record — and renders it as a visual self-map you can explore in a browser.
The skill knows when to push, when to go deeper, and when to tell you a problem isn't real. It doesn't tell you what to build. It helps you find problems worth solving and gives you the tools to test whether they're real.
You type /idea-finder. The skill interviews you across 13 structured blocks: your career history, your daily frustrations, your hobbies and communities, your personal life situations, and — critically — the specific people in your network.
By the end, you have a Roles List: every identity you inhabit (software engineer, homeowner, immigrant, mountain biker, parent) treated as a potential market.
The skill runs web searches for each role: what do people in this role struggle with, what workarounds do they use, what new technology could change the picture, how large is the market? Raw research lives in discovery.md; clean summaries surface in the visual map.
You return, the skill loads your document, and you go deeper. You run targeted digs on your most promising roles, prep for and debrief customer interviews, simulate skeptical customers, and gradually narrow toward one problem worth pursuing.
A ranked list of candidate problems scored on pain intensity, frequency, willingness to pay, founder fit, and market accessibility — plus a visual self-map, a founder brief you can share, and a single recommended next action at any point.
Recommended:
npx skills add zhenya-vlasov/idea-finder
Or manually:
# Clone the repo
git clone git@github.com:zhenya-vlasov/idea-finder.git ~/idea-finder
# Symlink the skill
ln -s ~/idea-finder/skills/idea-finder ~/.claude/skills/idea-finder
Open Claude Code and type /idea-finder to begin.