🦈 startup-idea-validator
Stress-test a startup idea with a VC, customer and competitor panel, cheap experiments and a verdict. A free, open-source Agent Skill for Claude Code, Cline, Cursor, Codex and 75+ AI agents.
Install startup-idea-validator
# Claude Code (all 51 skills)
/plugin install all-skills --marketplace milad-ahmd/agent-skills
# Cursor, Codex, Cline, Windsurf, Copilot + 75 more agents
npx skills add milad-ahmd/agent-skills --skill startup-idea-validator
# Shell installer
curl -fsSL https://raw.githubusercontent.com/milad-ahmd/agent-skills/main/install.sh | bash -s -- startup-idea-validatorIncluded in packs: indie-hacker-pack
What to say to your agent
Validate my startup idea: ...What could kill this idea?
When it triggers
Stress-tests a startup or product idea before you build it. It runs critique from a skeptical investor, a target customer, and a competitor, researches existing competitors, ranks the riskiest assumptions, writes Mom-Test interview questions, designs cheap validation experiments with success thresholds, and gives a Go, Pivot, or Kill verdict. Use when the user shares a startup, app, SaaS, or side-project idea and asks whether it's good, how to validate it, or what could kill it.
Full skill instructions (SKILL.md)
Startup Idea Validator
Kill bad ideas cheaply, and make good ones sharper.
1. Restate the idea as a testable hypothesis
[Customer segment] has [problem] that happens [frequency], currently solved by [alternative], and will [pay / switch / use] for [solution] because [unique insight]. Ask the user for anything missing: who, what problem, why now, and why them.
2. The panel (3 short critiques, in character)
- 🦈 Skeptical VC: market size logic, moat, distribution, "why won't Google or OpenAI do this?"
- 🙋 Target customer: "Do I actually have this problem? What do I use today? Would I pay, and how much?"
- ⚔️ Competitor CEO: "How would I crush or copy this in 3 months?"
3. Market reality check
- Competitors and alternatives, including "do nothing", spreadsheets and manual workarounds. Use web search if it's available and cite your sources. Otherwise ask the user.
- Where competitors are weak (look in their reviews, see
competitor-spy). - Market size only from cited sources, or a clearly labelled bottom-up estimate (customers × price × frequency).
4. Riskiest assumptions (ranked)
| Assumption | Type | Risk if wrong | Evidence today |
|---|---|---|---|
| Freelancers lose >2h/week on invoicing | Desirability | 🔴 fatal | none |
Types: desirability (do people want it?), viability (will they pay, can it make money?), feasibility (can we build and distribute it?).
5. Cheapest experiments (1–2 weeks each)
For the top 3 assumptions, pick from: 10 customer interviews (Mom Test), a landing-page smoke test with a waitlist, a concierge or manual MVP, pre-sales or letters of intent, a fake-door feature, or community posts. Define the success threshold before running the experiment. For example: "≥ 8 of 10 interviewees describe the problem unprompted" or "≥ 5% of landing-page visitors join the waitlist".
6. Mom Test interview script
8–10 questions about their past behaviour, not about your idea ("Tell me about the last time you…", "What did you try?", "What did it cost you?"). Avoid "Would you use…?".
7. Verdict
🟢 Go / 🟡 Pivot / 🔴 Kill, with a confidence level, the 2–3 reasons behind it, what evidence would change the verdict, and a 2-week action plan.
Rules
- Be candid, but always constructive. Attack the idea, never the founder.
- No invented statistics, market sizes or competitor revenue. Cite them or label them as estimates.
- This is not financial or legal advice.