What problem does it solve? Evaluating an ETF requires checking trend, risk, liquidity, cost, tracking error, and theme signals across scattered sources, and it is easy to overlook missing data or misuse leveraged products. This Skill runs a structured AlphaGBM workflow that scores a plain, non-leveraged ETF while explicitly preserving data gaps instead of guessing. ## Core Features & Use Cases - Multi-factor ETF scoring: Scores observed trend, risk, liquidity, cost, tracking, theme, and event inputs through the AlphaGBM strategy-workflows.v1 backend. - Missing-data preservation: Keeps status and missingData markers intact and never fills gaps from model memory or demo data; leveraged and inverse ETFs are rejected. - Controlled paid access: Requires ALPHAGBM_API_KEY in the environment and an explicit --confirm-usage flag after user approval before any allowance-consuming call. - Use Case: Ask your AI to evaluate SPY as an ETF strategy opportunity and receive a factor-by-factor breakdown, cost and tracking gaps, and concrete next verification checks in English or Chinese. ## Quick Start Use AlphaGBM to evaluate an ETF strategy opportunity for SPY, showing factor evidence, missing data and next checks.
