Metric Dashboard Skill for ChatGPT: Define a North Star and Alerts
Draft a measurement plan for a product or feature. Break the North Star into input metrics, specify formulas and data sources, add owners and thresholds, then sketch executive and operational dashboards.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download skills/metric-dashboard/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for metric-dashboard together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that metric-dashboard appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
A fictional reading app had 100 new users, with 60 completing a first save. Propose a North Star of weekly active readers who save at least once. Plan the events, use new registrations as the first-save-rate denominator, and treat 55% as a proposed warning threshold.What to check
The metric tree should keep the North Star and first-save rate distinct. It should calculate the sample baseline as 60/100 = 60%, label 55% as proposed, and describe weekly signup cohorts and remaining validation work.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should total signups be the North Star metric?
Start with the value the product delivers. If that value is finding and saving something to read, use signups as an acquisition input and put the value-delivering action and time window in the North Star.