/motherduck-share-data
Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access/visibility/update modes, GRANT READ ON SHARE, attaching share
$ npx -y skills add motherduckdb/agent-skills --skill motherduck-share-data --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/motherduck-share-data
Context preview
The summary Claude sees to decide when to auto-load this skill.
Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access/visibility/update modes, GRANT READ ON SHARE, attaching share
SKILL.md
motherduck-share-data.SKILL.mdname: motherduck-share-data
description: Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access/visibility/update modes, GRANT READ ON SHARE, attaching share URLs, UPDATE SHARE, and REFRESH DATABASE.
license: MIT
Share Data with MotherDuck
Use this skill when you need to distribute a MotherDuck database without copying data. Shares are read-only, zero-copy database clones and should be treated as explicit provisioning operations.
Source Of Truth
- Prefer the current MotherDuck sharing docs and SQL reference first.
- If the MotherDuck MCP `ask_docs_question` feature is available, use it before falling back to public docs.
- Keep the sharing model aligned with the documented behavior:
- zero-copy and metadata-only
- database-granularity sharing
- read-only recipients
- owner-controlled update mode
Prerequisites
- MotherDuck connection established via `motherduck-connect`
- Source database identified via `motherduck-explore`
- Share SQL validated via `motherduck-query`
Default Posture
- Default internal sharing to `ACCESS ORGANIZATION`, `VISIBILITY DISCOVERABLE`, and `UPDATE AUTOMATIC`.
- Use `UPDATE MANUAL` when the recipient needs a stable snapshot or versioned delivery.
- Use `ACCESS RESTRICTED` or `VISIBILITY HIDDEN` when distribution should stay tightly controlled.
- Confirm whether the recipient is an internal user, another organization, or public before choosing access and visibility.
- For write-heavy publishers, verify the DuckDB client version is one MotherDuck supports before relying on checkpoint or concurrent-write behavior during share-update workflows.
- Never treat a share as row-level security. Shares operate at database granularity.
Workflow
1. Identify the exact database to publish and who should consume it. 2. Decide sensitivity, discoverability, and freshness requirements before writing SQL. 3. Create the share with explicit access, visibility, and update settings. 4. If access is restricted, grant readers explicitly. If the share is hidden or link-based, distribute the share URL directly. 5. Have recipients `ATTACH` the shared database and query it read-only. 6. If the share uses `UPDATE MANUAL`, the owner runs `UPDATE SHARE` and consumers run `REFRESH DATABASE` when a new snapshot is ready.
For answer, review, or planning requests, return the sharing design and SQL without provisioning. For create, update, grant, or revoke requests, perform the requested in-scope operation and validate the resulting access; ask before public exposure, destructive revocation, or unrelated grants.
Open Next
- Read `references/SHARE_PLAYBOOK.md` for the full SQL playbook, access/update decision matrix, consumer workflow, and common failure modes.
Related Skills
- `motherduck-connect` for MotherDuck authentication and connection setup
- `motherduck-explore` for discovering databases, tables, columns, and existing shares
- `motherduck-query` for validating share SQL and downstream queries
- `motherduck-duckdb-sql` for DuckDB SQL syntax and lookup support
Read more
name: motherduck-share-data description: Create and manage MotherDuck data shares for zero-copy, read-only data distribution. Use whenever someone wants to share a database with team members, another organization, or the public — covers CREATE SHARE, access/visibility/update modes, GRANT READ ON SHARE, attaching share URLs, UPDATE SHARE, and REFRESH DATABASE. license: MIT
Share Data with MotherDuck
Use this skill when you need to distribute a MotherDuck database without copying data. Shares are read-only, zero-copy database clones and should be treated as explicit provisioning operations.
Source Of Truth
- Prefer the current MotherDuck sharing docs and SQL reference first.
- If the MotherDuck MCP `ask_docs_question` feature is available, use it before falling back to public docs.
- Keep the sharing model aligned with the documented behavior:
- zero-copy and metadata-only
- database-granularity sharing
- read-only recipients
- owner-controlled update mode
Prerequisites
- MotherDuck connection established via `motherduck-connect`
- Source database identified via `motherduck-explore`
- Share SQL validated via `motherduck-query`
Default Posture
- Default internal sharing to `ACCESS ORGANIZATION`, `VISIBILITY DISCOVERABLE`, and `UPDATE AUTOMATIC`.
- Use `UPDATE MANUAL` when the recipient needs a stable snapshot or versioned delivery.
- Use `ACCESS RESTRICTED` or `VISIBILITY HIDDEN` when distribution should stay tightly controlled.
- Confirm whether the recipient is an internal user, another organization, or public before choosing access and visibility.
- For write-heavy publishers, verify the DuckDB client version is one MotherDuck supports before relying on checkpoint or concurrent-write behavior during share-update workflows.
- Never treat a share as row-level security. Shares operate at database granularity.
Workflow
1. Identify the exact database to publish and who should consume it. 2. Decide sensitivity, discoverability, and freshness requirements before writing SQL. 3. Create the share with explicit access, visibility, and update settings. 4. If access is restricted, grant readers explicitly. If the share is hidden or link-based, distribute the share URL directly. 5. Have recipients `ATTACH` the shared database and query it read-only. 6. If the share uses `UPDATE MANUAL`, the owner runs `UPDATE SHARE` and consumers run `REFRESH DATABASE` when a new snapshot is ready.
For answer, review, or planning requests, return the sharing design and SQL without provisioning. For create, update, grant, or revoke requests, perform the requested in-scope operation and validate the resulting access; ask before public exposure, destructive revocation, or unrelated grants.
Open Next
- Read `references/SHARE_PLAYBOOK.md` for the full SQL playbook, access/update decision matrix, consumer workflow, and common failure modes.
Related Skills
- `motherduck-connect` for MotherDuck authentication and connection setup
- `motherduck-explore` for discovering databases, tables, columns, and existing shares
- `motherduck-query` for validating share SQL and downstream queries
- `motherduck-duckdb-sql` for DuckDB SQL syntax and lookup support
Opinionated AI agent skills for building applications with MotherDuck
Other skills on motherduckdb-agent-skills.
- /motherduck-build-cfa-app
Design a MotherDuck-backed customer-facing analytics app. Use for embedded analytics, multi-tenant SaaS reporting, or product analytics for external users -- whenever the decision depends on per-customer isolation, backend routing, service-account boundaries, read scaling, or
Open skill - /motherduck-build-dashboard
Build a live MotherDuck dashboard as a Dive. Use when composing one shareable KPI, trend, and breakdown story over existing MotherDuck data, especially when the result should stay a saved workspace artifact rather than a full application.
Open skill - /motherduck-build-data-pipeline
Design an end-to-end MotherDuck data pipeline. Use for ETL/ELT workflows -- choosing raw, staging, and analytics boundaries, bulk ingestion paths, transformation sequencing, dlt/dbt integration, publication targets, or whether DuckLake is actually required.
Open skill - /motherduck-connect
Connect to MotherDuck from any application. Use when setting up database connectivity via the Postgres endpoint (recommended), pg_duckdb, native DuckDB API, or JDBC. Covers connection strings, authentication, SSL, and environment variable configuration.
Open skill - /motherduck-create-dive
Create, edit, manage, share, or embed MotherDuck Dives — live React + SQL dashboards, charts, and data apps saved in the workspace. Use for any dashboard, chart, KPI display, or data visualization over MotherDuck data, and for Dive authoring mechanics such as get_dive_guide,
Open skill - /motherduck-create-flight
Create, schedule, run, and debug MotherDuck Flights — Python jobs that run on MotherDuck compute. Use whenever someone wants to create a flight, schedule a Python script or recurring job on MotherDuck, set up scheduled ingestion from Postgres, dlt sources, S3, BigQuery,
Open skill

