Menú
Rules and strategies for exploring databases, tables, schemas, and searching metadata.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Complex rules for calling render_chart, inferring axes, and choosing chart types based on user intent.
Diagnose a ClickHouse server error (code/name/exception) and give a concrete, actionable fix.
Diagnose part/partition health of a MergeTree table — too many parts, slow/stuck merges, bad partition key.
Rules for using explain/analyze/optimize tools to help the user tune their queries.
Diagnose a column/table schema issue — Nullable overhead, oversized integer, or weak compression — and propose an ALTER.
Strict rules on outputting ClickHouse syntax, limiting rows, and rendering SQL in markdown.
| name | data-exploration |
| description | Rules and strategies for exploring databases, tables, schemas, and searching metadata. |
The user wants to discover or understand the data model: which databases/tables exist, what columns a table has, where a particular field lives, how big a table is, or what the data looks like. Not for live server health (use system-troubleshooting) or running a query the user already described (use sql-generation).
list_databases — find available databases.list_tables — tables inside a chosen database.get_table_schema / get_table_ddl — columns + types (DDL also shows engine, keys, indexes) before reasoning about a table.search_columns — when the user wants a field but doesn't know the table (e.g. "where is revenue?" → search %revenue%).get_table_size — row count + on-disk size.get_table_sample — preview the first rows to verify contents.get_database_info — a database overview (table count + total size).