From motherduck-skills
DuckDB SQL reference for MotherDuck. Use when you need exact DuckDB syntax or function behavior, friendly SQL features like QUALIFY, GROUP BY ALL, or list/struct types, MotherDuck-specific SQL such as shares, secrets, snapshots, or UNDROP, or to fix SQL errors and PostgreSQL-style SQL that fails on MotherDuck.
How this skill is triggered — by the user, by Claude, or both
Slash command
/motherduck-skills:motherduck-duckdb-sqlThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when you need exact DuckDB syntax, function behavior, or a quick sanity check that a statement will actually work on MotherDuck.
Use this skill when you need exact DuckDB syntax, function behavior, or a quick sanity check that a statement will actually work on MotherDuck.
"database"."schema"."table" names once more than one database or share is in scope.GROUP BY ALL, QUALIFY, UNION BY NAME, arg_max, EXCLUDE, and REPLACE.VARIANT, native GEOMETRY, MERGE INTO, or date_trunc return-type changes.UNDROP DATABASE statements as operational SQL with plan-specific retention behavior, not ordinary analytical syntax.references/SYNTAX_REFERENCE.md.references/SYNTAX_REFERENCE.md for DuckDB data types, friendly SQL features, functions, complex types, and common MotherDuck-specific gotchas.motherduck-query for writing and validating analytical SQL against live MotherDuck datamotherduck-connect when syntax support depends on PG endpoint versus native DuckDB behaviormotherduck-explore when the problem is really missing schema context rather than missing syntax knowledgenpx claudepluginhub motherduckdb/agent-skills --plugin motherduck-skillsExecute DuckDB SQL queries against MotherDuck databases. Use when running analytics, aggregations, transformations, or any SQL operation. Covers query best practices, CTEs, window functions, QUALIFY, and performance optimization.
Executes raw SQL or natural language queries against attached DuckDB databases or ad-hoc files. Manages session state, schema retrieval, and result size estimation.
Sets up and manages OpenDuck, an open-source distributed DuckDB with differential storage, hybrid dual execution, and transparent remote database attach via gRPC + Arrow IPC.