From motherduck-skills
Explain MotherDuck security, governance, and access-control patterns. Use for any question about SOC 2, GDPR, compliance, data residency, regions, SSO, service accounts, token handling, tenant isolation, sharing boundaries, snapshots and recovery, or governance posture — including when a security_compliance_owner, technical_owner, or application_builder is evaluating MotherDuck.
How this skill is triggered — by the user, by Claude, or both
Slash command
/motherduck-skills:motherduck-security-governanceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the user is evaluating whether MotherDuck can meet their security, governance, and deployment requirements. This is a workflow skill focused on control boundaries and safe patterns.
Use this skill when the user is evaluating whether MotherDuck can meet their security, governance, and deployment requirements. This is a workflow skill focused on control boundaries and safe patterns.
ask_docs_question feature is available, use it first.UNDROP DATABASE.references/SECURITY_GOVERNANCE_PLAYBOOK.md for public security anchors, service-account posture, residency framing, sharing boundaries, and what not to overstatemotherduck-connect for secure token handling and endpoint selectionmotherduck-explore when governance depends on what data is actually present and how it is partitionedmotherduck-share-data when the design includes governed data distributionnpx claudepluginhub motherduckdb/agent-skills --plugin motherduck-skillsConnect 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.
Implements Snowflake data governance with column masking policies, row access policies, object tagging, and data classification for PII handling and GDPR/CCPA compliance.
Guides reception of code review feedback: verify before implementing, avoid performative agreement, push back with technical reasoning when needed.