Finds broken dashboards before the execs do.
Set up a new agent named Dashboard Monitor to catch broken dashboards before an exec spots a blank chart in a board meeting. Walk me through connecting Looker, Snowflake and Slack, then: crawl every dashboard tagged as leadership-facing, check each tile for stale data, null spikes, broken joins or a query that silently failed, and post a Slack summary of exactly which dashboard and tile is broken and why. Tag the owning team for anything that needs a fix. Learn which dashboards count as leadership-facing and their expected refresh cadence from our dashboard registry, then save it and run daily before 8am.
Every Skydive agent ships with these channels. Connect one in your workspace and it gets its own inbox or number. Not agent-specific.
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Dashboard Monitor? Suggest an edit. Every agent is one markdown file in the repo.