Explore
Use this to make sense of a database, warehouse, or DuckDB file: inventory and rank what is there, profile columns, detect PII, flag grain and data-quality problems, infer and verify how tables join, and answer ad-hoc data questions with guarded SQL probes, producing a draft map without dumping the schema into context. Trigger it for casual, artifact-first prompts like "what''s in my duckdb", "wh…
No Em Dashes
Enforce em-dash-free writing. Use this skill whenever you write or edit prose for the user, including drafts, emails, essays, reports, documentation, blog and social posts, marketing copy, creative writing, summaries, and rewrites, so the output contains zero em dashes and avoids the grammatical structures that invite them. Replace em-dash constructions with commas, semicolons, colons, periods, o…
Transform
Use this to author and change a dbt project: bootstrap a new dbt project in a repo that has none (`transform init`), write or refactor dbt model SQL from staging to marts, add tests and docs in schema.yml, manage dependencies, and define or update the semantic layer (dbt semantic models / MetricFlow: entities, dimensions, measures, metrics). Trigger it for requests like "set up a dbt project in t…
Maintain
Use this to keep a dbt project correct as the warehouse and the business change. It detects drift on four axes and proposes the fix: schema drift (source columns and tables added, dropped, retyped, or renamed), volume drift (a row count that collapsed, a table that emptied, a load that half-failed), grain drift (a key that lost uniqueness, a changed row-per-entity cardinality, an increased join f…