product-metrics-definitions
Skill0 starsChanged 20 days agoMITView on GitHub
Write one clear, agreed definition for each product metric — what it measures, the exact formula, the data source, what counts and what doesn't, and who owns it — so every dashboard and meeting means the same thing by the same word. Use when someone asks to define a metric, build a metrics glossary or dictionary, settle a "which number is right" argument, or document KPIs.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beta-program-managerSkill
- cross-team-dependency-mapSkill
- customer-advisory-board-prepSkill
- data-request-routerSkill
- decision-logSkill
- deprecation-planSkill
- duplicate-request-mergingSkill
- experiment-logSkill
- feature-flag-trackingSkill
- feedback-taggingSkill
- information-debt-auditSkill
- internal-enablement-briefSkill
- kpi-health-checkSkill
- launch-readiness-checklistSkill
- meeting-to-action-converterSkill
- new-pm-onboarding-packSkill
- pricing-packaging-change-logSkill
- process-documentationSkill
- product-ops-contextSkill
- quarterly-planning-prepSkill
- raci-builderSkill
- release-notes-draftingSkill
- request-intake-triageSkill
- retro-facilitationSkill
- ritual-calendarSkill
- roadmap-hygieneSkill
- sprint-review-summarySkill
- support-escalation-patternsSkill
- tool-stack-auditSkill
- vendor-evaluation-scorecardSkill
- voice-of-customer-digestSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Don't pick a winner yourself.
- Distinctive: line 45
If a field isn't known from the source, write "Unknown — confirm with [likely owner]."
- Distinctive: line 62
When a definition changes, keep the old one under "Last changed" so past reports still make sense.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product metrics definitions
Most metric fights aren't about the number. They're about two people using the same word for different things. A definition settles it once.
Before you start
If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.
Step 1: Collect every version
For each metric in scope, gather every way it's currently being defined or calculated: dashboards, decks, spreadsheets, what people said. If versions differ, list them side by side before writing anything.
| Metric | Where it's used | How it's calculated there | Gives a different number? |
Don't pick a winner yourself. If versions conflict, show the conflict and name who should decide.
Step 2: Write the definition
### [Metric name]
- **Plain-language meaning:** [one sentence a new hire would understand]
- **Formula:** [exact calculation, e.g. accounts with 1+ active session in 28 days ÷ total paying accounts]
- **Counts:** [what's included]
- **Doesn't count:** [exclusions: test accounts, internal users, free trials, refunds]
- **Time window:** [daily, 7-day rolling, calendar month]
- **Data source:** [system and table or report name]
- **Refreshes:** [how often]
- **Owner:** [person who answers questions and approves changes]
- **Good direction:** [up / down / within a range]
- **Often confused with:** [similar metrics and how they differ]
- **Last changed:** [date and what changed]Rules:
- The plain-language meaning must not use the metric's own name to define it.
- "Active," "engaged," "retained," and "user" always need a precise meaning. Spell it out every time.
- If a field isn't known from the source, write "Unknown — confirm with [likely owner]."
- One metric per entry. If one name covers two calculations, split it into two metrics with different names.
Step 3: Build the glossary
# Product metrics glossary — Last updated [date]
| Metric | Meaning | Owner |
|---|---|---|
[Full definitions below, alphabetical]
## Conflicts to resolve
- [Metric]: [version A] vs [version B] — Decide: [name]When a definition changes, keep the old one under "Last changed" so past reports still make sense.
Related skills
- kpi-health-check — check how the defined numbers are moving
- data-request-router — route new number requests to the right definition
- experiment-log — use the same definitions for success metrics
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

