app-teardownlisted

# App Teardown Studies a live product the way a chef eats at a rival's restaurant: walk the real flows, name what works, explain WHY it works for them, and decide what transfers to our context. The output is a decision artifact, not a tour. ## Use When - A live app/product should be mined for ideas applicable to one of our projects. - Before building a surface that a named competitor/product already does well. - User names a product and asks what to learn, steal, or adapt from it. ## Do Not Use When - Target is a repo/codebase → `code-teardown`. - Only visual direction is wanted (moodboard, type, palette) → `frontend-reference-hunt`. - Understanding OUR OWN system's internals → `doc-and-modernize`. ## Inputs / Prereqs - Target URL + whether login is needed (drive the user's Chrome via `claude-in-chrome`). - OUR context lock: which project the ideas land in, its goals and constraints. - Memory state-check FIRST: `reference_<target>_evaluated_*` note exists → surface prior outcome and stop unless the revisit condition is met. ## Workflow 1. **Scope + constraint capture** — target, key flows to walk, and the gate question: why does their design work FOR THEM (scale, audience, pricing model, compliance, platform, legacy)? Record it; it powers the cargo-cult gate later. 2. **Live exploration** (claude-in-chrome) — walk onboarding, core flow, settings, empty states, error recovery, upgrade/paywall moments. Screenshot each finding into `<project>/.claude/desig