Share Data
Apps & Automationshare-dataShare Data is an Agent Skill for apps & automation published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Create and manage MotherDuck data shares for zero-copy data distribution. Use when sharing databases with team members, other organizations, or making data publicly available.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/share-data-motherduckdb-agent-skills/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/share-data, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
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_questionfeature 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
connect - Source database identified via
explore - Share SQL validated via
query
Default Posture
- Default internal sharing to
ACCESS ORGANIZATION,VISIBILITY DISCOVERABLE, andUPDATE AUTOMATIC. - Use
UPDATE MANUALwhen the recipient needs a stable snapshot or versioned delivery. - Use
ACCESS RESTRICTEDorVISIBILITY HIDDENwhen distribution should stay tightly controlled. - Never treat a share as row-level security. Shares operate at database granularity.
Workflow
- Identify the exact database to publish and who should consume it.
- Decide sensitivity, discoverability, and freshness requirements before writing SQL.
- Create the share with explicit access, visibility, and update settings.
- If access is restricted, grant readers explicitly. If the share is hidden or link-based, distribute the share URL directly.
- Have recipients
ATTACHthe shared database and query it read-only. - If the share uses
UPDATE MANUAL, the owner runsUPDATE SHAREand consumers runREFRESH DATABASEwhen a new snapshot is ready.
Open Next
references/SHARE_PLAYBOOK.mdfor the full SQL playbook, access/update decision matrix, consumer workflow, and common failure modes
Related Skills
connectfor MotherDuck authentication and connection setupexplorefor discovering databases, tables, columns, and existing sharesqueryfor validating share SQL and downstream queriesduckdb-sqlfor DuckDB SQL syntax and lookup support