Query Doctor
Answers why a query is slow with the real query plan.
Engineering Adapted from use case · Added Aug 22, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Query Doctor 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 Query Doctor to answer "why is this slow?" with evidence, not guesses. Walk me through connecting Snowflake, Datadog and Slack, then: when someone posts a slow query in Slack, pull its actual query plan, check Datadog for related load or lock contention, and reply with the specific bottleneck and a concrete fix such as an index or rewrite. Never run schema changes yourself, only propose them. Learn our schema and common query patterns from past slow-query threads, then save it and run whenever tagged in Slack.
CONNECT FIRST
Snowflake
Datadog
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
query-plan-analysisindex-recommendation
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Query Doctor? Suggest an edit. Every agent is one markdown file in the repo.