DuckDB SQL Reference for MotherDuck
SkillDatabases & dataDuckDB 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
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the DuckDB SQL Reference for MotherDuck skill
What this skill tells your AI
The instructions your AI receives, as published by motherduckdb/agent-skills in skills/motherduck-duckdb-sql/SKILL.md and read by ahel’s review.
Source Of Truth
- Prefer current DuckDB SQL docs for language features and function semantics.
- Use current MotherDuck SQL docs for MotherDuck-only commands such as shares, secrets, snapshots, and Dive operations.
- MotherDuck can lag upstream DuckDB releases for client compatibility; check MotherDuck version-lifecycle docs before promising newly released DuckDB syntax or types are available.
- If the connection path matters, verify behavior against the current Postgres-endpoint docs before promising server-mode support.
Default Posture
- Write DuckDB SQL, not PostgreSQL SQL, even when the client connects through the Postgres endpoint.
- Use fully qualified
"database"."schema"."table"names once more than one database or share is in scope. - Prefer DuckDB-native constructs when they simplify the query:
GROUP BY ALL,QUALIFY,UNION BY NAME,arg_max,EXCLUDE, andREPLACE. - When porting SQL from another engine, translate functions, date arithmetic, identifier quoting, and type casts explicitly instead of assuming compatibility.
- Verify current MotherDuck support before relying on recently released upstream DuckDB features such as
VARIANT, nativeGEOMETRY,MERGE INTO, ordate_truncreturn-type changes. - Check whether the statement depends on local files, extension install/load, temporary-table behavior, or other client-only features before claiming it will work in MotherDuck.
- Treat snapshot, restore, and
UNDROP DATABASEstatements as operational SQL with plan-specific retention behavior, not ordinary analytical syntax. - Treat
INCLUDE_PATTERNas whole-table/view filtering on a Share, not row-level or column-level security. UseALTER SHAREonly for include-pattern changes. - Distinguish physical import (
CREATE DATABASE ... FROM '<file-url>') from zero-copy clone sources, and reject filtered shares as clone sources. - Use role/grant SQL for governed access and audit it with
SHOW ...statements; do not preserveACCESS ORGANIZATIONas the preferred RBAC pattern. - Treat MotherDuck SQL as an additional surface on top of DuckDB SQL, not a replacement for it.
Workflow
- Confirm the connection path and whether the question is about syntax, feature support, or a specific error.
- Write or repair the statement in DuckDB SQL first.
- Verify any MotherDuck-only command or server-mode limitation against the current docs.
- If the user needs exact syntax or function details, open
references/SYNTAX_REFERENCE.md.
References
Read only the reference sections needed for the current task.
- Read
references/SYNTAX_REFERENCE.mdfor DuckDB data types, friendly SQL features, functions, complex types, and common MotherDuck-specific gotchas.
Related Skills
Load related skills only for missing capabilities; reuse established context.
motherduck-queryfor writing and validating analytical SQL against live MotherDuck datamotherduck-connectwhen syntax support depends on PG endpoint versus native DuckDB behaviormotherduck-explorewhen the problem is really missing schema context rather than missing syntax knowledge
Signals
- GitHub stars
- 58
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
motherduck-duckdb-sql- Source
- github.com/motherduckdb/agent-skills