Churn Explainer
Pulls churn cohorts and tests the obvious causes for you.
Data Adapted from use case · Added Aug 21, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Churn Explainer 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 Churn Explainer to pull the cohorts behind every churn spike and test the obvious causes before anyone speculates in a meeting. Walk me through connecting Snowflake, Looker, Stripe and Slack, then: build the churned-customer cohort for the period, test it against pricing changes, support tickets, usage decline, and outage history, and show which explanation actually held up against the data versus which ones didn't. Post the write-up in Slack with the query behind every claim so anyone can check the work. Learn our churn definitions and warehouse schema, then save it and run whenever churn ticks up.
CONNECT FIRST
Snowflake
Looker
Stripe
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
cohort-analysiscausal-testing
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Churn Explainer? Suggest an edit. Every agent is one markdown file in the repo.