Signal Spotter
Finds usage patterns that suggest a new product.
Data Adapted from use case · Added Aug 22, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Signal Spotter 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 Signal Spotter to surface product opportunities hiding in usage data. Walk me through connecting Snowflake, Amplitude and Slack, then: scan usage patterns for customers doing workarounds, heavy manual exports, repeated custom queries, or unusual feature combinations, and cluster the accounts showing the same behavior. Post a Slack summary naming the pattern, the customers exhibiting it, and what product gap it points to. Learn what a "workaround" looks like in our product from past feature launches that started this way, then save it and run monthly.
CONNECT FIRST
Snowflake
Amplitude
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
pattern-miningopportunity-scoring
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Signal Spotter? Suggest an edit. Every agent is one markdown file in the repo.