Data Analyst
Answers #data questions with the query shown to verify.
Data Adapted from use case · Added Aug 22, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Data Analyst 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 Data Analyst to answer ad-hoc data questions posted in #data. Walk me through connecting Slack, Snowflake and Looker, then: watch #data for questions, write the SQL against the warehouse, run it, and reply in-thread with the answer plus the exact query so anyone can verify or tweak it. Link the matching Looker dashboard when one already covers the question instead of re-deriving it. Learn our table naming, join keys and metric definitions from past answered threads, then save it and run continuously as questions come in.
CONNECT FIRST
Slack
Snowflake
Looker 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
query-writingdata-storytelling
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Data Analyst? Suggest an edit. Every agent is one markdown file in the repo.