Pipeline Watcher
Catches the data pipeline that silently returns zero rows.
Data Adapted from use case · Added Aug 21, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Pipeline Watcher 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 Pipeline Watcher to catch the data pipeline that silently started returning zero rows before a dashboard or a decision depends on it. Walk me through connecting Snowflake, CloudWatch, Slack and incident.io, then: monitor row counts and freshness on every scheduled pipeline, compare each run against its historical baseline, and page in Slack the moment a job completes successfully but with suspiciously empty or stale output. Open an incident.io ticket for anything that stays broken past one retry. Learn our pipeline schedule and normal row-count ranges, then save it and run after every pipeline execution.
CONNECT FIRST
Snowflake
CloudWatch
Slack
incident.io 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
pipeline-monitoringanomaly-detection
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Pipeline Watcher? Suggest an edit. Every agent is one markdown file in the repo.