Smart Store Site Selection Engine

Problem It Solves

Store site selection often fails in two ways: the model improvises a location without customer segment, business format, or operating strategy, or it crosses data boundaries by inventing competitor counts, transit details, or scores. smart-site-selection-skill turns the task into a controlled SOP: validate key parameters, fetch only verifiable coordinates, then hand off detailed computation and rendering to a Python backend.

How It Works

• Hard-stop validation: if core customer segment or store strategy is missing, it triggers message or proactive-agent and ends the turn instead of continuing.
• Coordinate fetching only: it uses the AMap POI plugin to retrieve top three qualifying locations with center coordinates, without querying transit, competitor, or business-facility details.
• Insight generation: it produces a macro-level market assessment and brief pros/cons notes for the three business districts.
• Report handoff: coordinates, location names, and generated insights are passed to the backend engine for an HTML report with ECharts and a static map.

Boundaries

It is suited for early-stage site selection when city, district, category, target segment, and store strategy are already defined. It should not be used for exact competitor store counts, transit point details, engineering conditions, or final scoring; those depend on the Python backend and required skills.