Rollout Specialist
Ramps traffic 1/10/50% and auto-rolls back on bad signals.
Engineering Adapted from use case · Added Aug 21, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Rollout Specialist 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 Rollout Specialist to run staged rollouts so I don't have to babysit them. Walk me through connecting Slack, CloudWatch and GitHub, then: when I say "ship it" in Slack, take the change through 1%, 10%, then 50% of traffic, watching error rate and the other signals we care about at each stage, and roll it back on its own the moment one moves out of bounds. Post status at each ramp step in Slack. Learn our rollback thresholds and which signals matter per service, then save it and run on every "ship it".
CONNECT FIRST
Slack
CloudWatch
GitHub 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
progressive-rolloutincident-reporting
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Rollout Specialist? Suggest an edit. Every agent is one markdown file in the repo.