Metric Definition Skill for ChatGPT: Specify Activation Rate Precisely
Write a product metric's category, formula, exclusions, time window, data source, and owner. Use it when reports share a metric name but calculate it differently.
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 pm-data-analytics/skills/metric-definition/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for metric-definition 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-definition 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
Define new-user activation for a fictional reading app. Count non-test accounts registered this week that save at least one article within seven days of signup. In the sample, 32 of 80 eligible accounts qualify. Request a full metric spec and a guardrail metric.What to check
Deduplicate by account, calculate 32/80 = 40%, exclude test accounts, and wait for the seven-day window to close before finalizing the cohort. A possible guardrail is the share of saves undone within 24 hours, with its rationale.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can I write the metric spec with only one current value?
Start with the definition, data source, owner, and review frequency. Label the known value as a sample or baseline and list missing fields and targets as follow-ups.