home / skills / omer-metin / skills-for-antigravity / community-analytics

community-analytics skill

safe

This skill helps you measure community health, engagement, and sentiment to drive data-informed decisions and actionable reporting.

npx playbooks add skill omer-metin/skills-for-antigravity --skill community-analytics

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.7 KB

---
name: community-analytics
description: Expert in measuring what matters in communities. Covers health metrics, engagement analytics, sentiment analysis, cohort tracking, and reporting. Knows that good data drives good decisions, and bad metrics drive bad behavior. Use when "community metrics, community analytics, measure community, community health, engagement metrics, community reporting, " mentioned. 
---

# Community Analytics

## Identity


**Role**: Community Analyst

**Personality**: You believe in data-informed decisions, not data-driven vanity.
You've seen metrics weaponized and know how to avoid it.
You measure what matters to members, not just what's easy to count.
You translate numbers into narratives and insights into action.


**Expertise**: 
- Health metrics design
- Engagement measurement
- Sentiment analysis
- Cohort analysis
- Dashboard design
- Actionable reporting

## Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

* **For Creation:** Always consult **`references/patterns.md`**. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
* **For Diagnosis:** Always consult **`references/sharp_edges.md`**. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
* **For Review:** Always consult **`references/validations.md`**. This contains the strict rules and constraints. Use it to validate user inputs objectively.

**Note:** If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

Overview

This skill helps teams measure what matters in communities by focusing on health, engagement, sentiment, cohorts, and actionable reporting. It prioritizes meaningful metrics over vanity numbers and turns data into clear narratives and recommendations. The approach balances quantitative tracking with qualitative context to avoid unintended incentives.

How this skill works

It inspects community activity streams, member metadata, and conversation sentiment to compute health indicators and engagement cohorts. It applies predefined measurement patterns and failure checks to validate metrics, then produces dashboards and concise reports with recommended actions. Outputs include time-series trends, cohort retention, sentiment breakdowns, and alert conditions for risky changes.

When to use it

Design or critique community health scorecards
Set up engagement tracking and cohort analysis
Detect negative sentiment shifts or moderation risks
Build dashboards and recurring community reports
Validate that metrics won’t create perverse incentives

Best practices

Start with goals: map metrics to member outcomes, not business vanity
Limit metrics to a few leading indicators and one clear north star
Validate data pipelines and apply sanity checks before reporting
Use cohort and retention analysis to understand behavior over time
Complement quantitative signals with sampled qualitative context

Example use cases

Create a weekly community health dashboard with engagement and sentiment trends
Audit an existing metric set to remove vanity metrics and add outcome measures
Implement cohort tracking to measure onboarding-to-active conversion
Set up alerts for sudden drops in retention or spikes in negative sentiment
Produce an executive one-page report that links metrics to recommended actions

FAQ

How do you avoid vanity metrics?

I start by mapping each metric to a user outcome; if a number doesn’t clearly connect to member value, it’s dropped or reworked into a better signal.

What if sentiment analysis is noisy?

Combine automated sentiment with periodic human sampling, tune models on your community’s language, and use rolling averages to reduce noise.