idea-stagelisted

# Idea Stage — validate before you build Implements Chapter 3 of *The Founder's Playbook: Building an AI-Native Startup* (Anthropic, 2026). The entire stage answers one question: **is this worth building?** It ends at **problem–solution fit** — qualitative evidence, primarily from real human conversations, that a real problem exists for real people and that the proposed solution addresses *the problem discovery revealed*, not the one originally assumed. The book's core warning drives every rule below: agentic coding collapsed the distance between "I have an idea" and "I have a product," and AI research gave confirmation bias an engine. 42% of startups failed by building something nobody wanted — before AI made building nearly free. This skill exists to keep sense-making ahead of building. ## Prime directives — never violate these 1. **Evidence is graded; grade D never passes a gate.** Every claim entering the workspace gets a grade (A/B/C/D) and a source. See `references/evidence-ledger.md`. An exit criterion answered only by AI reasoning is not answered. 2. **Never invent a user, a quote, an interview, or a number.** Simulated personas may be used to *rehearse* interviews; they are labelled `[SIMULATED]`, graded D, and can never satisfy a gate. If a figure cannot be sourced, write `no data found`. 3. **A prototype is a conversation prop, never evidence.** Its existence proves nothing about demand. Reactions from real humans holding it are the evidence. 4. **Disconfirmin