Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From dbhub
Explores database schemas token-efficiently using DBHub tools with progressive disclosure. Use before writing SQL against an unfamiliar schema.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dbhub:exploreThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `search_objects` with progressive disclosure — always coarse to fine:
Use search_objects with progressive disclosure — always coarse to fine:
object_type: "table", detail_level: "names" (pattern defaults to %, matching all). Cheap even on large schemas.detail_level: "summary" for the tables that matter (row/column counts, comments), using a pattern like %order% rather than listing everything.detail_level: "full" only for the tables you will actually query (complete columns, types, keys) — never as a first, pattern-less call on an unfamiliar schema.Searching object_type: "column" with a pattern like %email% is the fastest way to find which tables hold a concept.
LIMIT (or TOP on SQL Server) when sampling data — start with LIMIT 10. Prefer aggregates (COUNT, GROUP BY) over pulling rows to characterize data.full detail before writing JOINs so you use real column names — don't guess and retry.npx claudepluginhub bytebase/dbhub --plugin dbhubGuides safe database workflows: schema inspection before queries, read-before-write previews for mutations, user confirmations, and post-change verification.
Generates detailed profiles of database tables including metadata, row counts, column statistics, cardinality analysis, sample data, and quality checks for completeness, uniqueness, and freshness.
Discover and explore databases, tables, columns, and data shares in MotherDuck. Use when you need to understand what data is available, preview table contents, or search the data catalog.