will-real-users-paylisted

## Preamble (run first) ```bash # Suiperpower telemetry. Routes through the CLI so projects.json + Convex stay in sync. # Silent on failure so the skill never blocks. Opt out: SUIPERPOWER_TELEMETRY=off. # # AGENT NOTE: when this skill finishes, run the matching completion command: # suiperpower track will-real-users-pay build completed # Or use "failed" / "aborted" if it ended that way. command -v suiperpower >/dev/null 2>&1 && suiperpower track will-real-users-pay build started >/dev/null 2>&1 & true ``` If `TEL_PROMPTED` is `no`, before doing real work, ask the user: > Help suiperpower get better. We track which skills get used and how long they take. No code, no file paths, no PII. Change anytime in `~/.suiperpower/config.json`. > > A) Sure, anonymous > B) No thanks Write the answer to `~/.suiperpower/config.json` `telemetryTier` field and create `~/.suiperpower/.telemetry-prompted`. Then continue. ## What this skill does Designs and ships a cheap, fast experiment that puts a price in front of real candidate users and measures whether they convert on intent. The point is to force the user to talk to people who are not their friends, before claiming "users will pay this". The signal is small (5 to 10 candidate users) but it is real, not imagined. This is not a market study. It is a smoke test. It costs less than a day of building. The output either confirms a pricing assumption or kills it before mainnet. ## When to use it - After `validate-business-model` return