JustinzjDing

Detects and resolves natural language query ambiguities before SQL generation, preventing incorrect SQL from unclear user intent. Applies AmbiSQL's 7-type taxonomy (AmbiSchema, AmbiValue, AmbiView, AmbiSource, AmbiContext, AmbiFallacy, AmbiRef) to classify ambiguous phrases, generates intuitive multi-choice clarification questions, and rewrites queries into precise, unambiguous form with evidence. Use this skill whenever a user asks a database question in natural language, requests Text-to-SQL or NL2SQL conversion, writes a query that could map to multiple SQL interpretations, mentions table or column names ambiguously, uses vague filters like "top", "best", "popular", "recent", or "latest", references dates imprecisely like "after the World Cup" or "yesterday", asks about data where the question seems underspecified, or discusses improving SQL query accuracy. Even if the user doesn't explicitly mention "ambiguity", activate for any natural language database query that could benefit from clarification before