Benchdive
All agents/Operations/Uptime Watcher

Uptime Watcher

Sees the status page move, tells customers first.

Operations Adapted from use case · Added Aug 22, 2026
Run Uptime 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.
View source

THE SETUP PROMPT

Set up a new agent named Uptime Watcher to get ahead of incidents instead of reacting to angry tickets. Walk me through connecting Statuspage, Slack and Zendesk, then: watch our status page and core health checks for a state change, and the moment an incident opens, draft a customer-facing update and post it in Slack for the on-call lead to approve within five minutes before it goes out on Statuspage and to affected accounts in Zendesk. Keep the update refreshed as the incident progresses and post the resolution notice once it clears. Learn our incident severity levels and messaging tone from past incident postmortems, then save it and run continuously.

CONNECT FIRST

SStatuspageSlackZendesk

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

incident-monitoringcustomer-communication

Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.

See something off with Uptime Watcher? Suggest an edit. Every agent is one markdown file in the repo.

Prompt copied. Send it to a Skydive agent as the first message