Ad Analyst
Explains why winning ads work and backlogs next tests.
Marketing Adapted from use case · Added Aug 22, 2026
Based on 231 ways to use an agent by @dhruvamin
Run Ad Analyst 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 Ad Analyst to explain the "why" behind winning ads instead of just reporting the numbers. Walk me through connecting Google Analytics and Slack, then: review the past week's ad performance, identify which creative, copy or targeting elements correlate with the winners, and write up the likely reason in plain language. Add three specific follow-up test ideas to a backlog and post the analysis in Slack. Learn our past test results and what's already been tried from the existing backlog, then save it and run weekly.
CONNECT FIRST
GGoogle Analytics
Slack
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
ad-performance-analysistest-planning
Reusable capabilities the prompt sets up. Browse the open skills ecosystem at skills.sh.
See something off with Ad Analyst? Suggest an edit. Every agent is one markdown file in the repo.