Metrics Librarian
Defines every metric once and flags queries that disagree.
Data Adapted from use case · Added Aug 21, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Metrics Librarian yourself. Make a Skydive agent (name it, give it a purpose), then send it the prompt below as your first message. It asks for what it needs and sets itself up. Free to copy, adapt, and edit after.
THE SETUP PROMPT
Set up a new agent named Metrics Librarian to keep one canonical definition for every metric we track and catch every query that quietly disagrees with it. Walk me through connecting Snowflake, Looker, Notion and Slack, then: maintain the definitions page in Notion, scan dashboards and saved queries in Looker and Snowflake for logic that drifts from the canonical definition, and flag every mismatch in Slack with the exact difference in the SQL. Learn our current metric definitions and who owns each one, then save it and run continuously as new queries and dashboards get added.
CONNECT FIRST
Snowflake
Looker
Notion
Slack TALKS TO YOU IN
SlackEmailiMessage
Every Skydive agent ships with these channels. Connect one in your workspace and it gets its own inbox or number. Not agent-specific.
SKILLS INSIDE
metric-definitionssql-diffing
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Metrics Librarian? Suggest an edit. Every agent is one markdown file in the repo.