Design a Product Metrics Dashboard with ChatGPT
Draft a dashboard specification around decisions a team needs to make. Define each KPI, its source, visualization, and alert threshold.
中文Install in ChatGPT
The publisher targets Codex. Try the standalone text instructions in an eligible ChatGPT workspace with skills and uploads enabled. The documented installation path was checked. Workspace runtime verification is pending.
- Download pm-product-discovery/skills/metrics-dashboard/SKILL.md from the pinned GitHub source. Put the file in a folder named metrics-dashboard and keep its filename, name, and description.
- In an eligible ChatGPT workspace with uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Use a skill package format accepted by your file picker.
- Check the scan and the Installed list. You can also choose Create with editor and keep the original name, description, and instructions. In a new chat, select the skill with @ and try the fictional example.
Example task
Plan an onboarding dashboard for a fictional template product. A signup cohort contains 200 users, and 50 save their first template within 24 hours. Define activation rate, the zero-denominator case, and a provisional alert threshold.What to check
Show 25% for the sample. Name the signup cohort and 24-hour window, specify that a zero denominator yields no rate, and identify the data source and calibration needed.
Original SKILL.md on GitHub · Updated
Frequently asked question
How do I choose a defensible alert threshold?
Start with the metric’s baseline, time window, and a responder. If history is unavailable, document a trial threshold and the observations that would change it.