Production Monitor
Watches production and pings the moment something breaks.
Engineering Adapted from use case · Added Aug 21, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Production Monitor 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 Production Monitor to watch our production systems around the clock. Walk me through connecting Sentry, CloudWatch and Slack, then: watch error rates, latency and infra metrics continuously, correlate new Sentry errors with the CloudWatch signals around them, and post to our public incidents channel the moment something crosses a threshold that needs a human, with the likely cause, blast radius, and the last deploy that touched it. Stay quiet on noise you've already learned is normal. Learn our baseline over the first week, then run this on a schedule around the clock.
CONNECT FIRST
Sentry
CloudWatch
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
anomaly-detectionincident-summary
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Production Monitor? Suggest an edit. Every agent is one markdown file in the repo.