3 skills for data teams
Postgres daily metrics from your own tables
Every morning: one number from a saved SQL query against your Postgres database, such as signups or orders, with the change since the day before.
FoundersEvery day at 8:00Stat tileUses PostgreSQL.Snowflake credit usage this week
Every Monday: Snowflake credits used in the last 7 days against the week before, by warehouse, with the most expensive queries and who ran them.
Data teamsMondays at 8:00Stat tileUses Snowflake.Databricks failed jobs
Every morning: Databricks job runs that failed or timed out since yesterday, with the failing task, the error line and a link, and an ask about repairing.
Data teamsEvery day at 7:30Asks youUses Databricks.What an agent can take off data teams’s plate
A data team fields two kinds of question all week: is the data fresh and the warehouse bill sane, and what do the numbers say. Both mean opening the same consoles and running the same queries, usually after someone has already noticed a problem.
These skills ask first. Snowflake credits by warehouse, BigQuery bytes billed by user and query, Databricks job runs that failed, dbt Cloud runs that failed and sources past their freshness threshold, the slowest queries from pg_stat_statements, one number from a saved Postgres query and the week-over-week movement on a Metabase dashboard. Give your agent a read-only role, run them on a schedule, and the team sees what broke before the stakeholders do.
Other teams
One board for every report data teams runs
Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.
Free during the open beta. No card.