mcpField
C
cohort-analysis

cohort-analysis

github.com/gtmagentsData & databases43065 installsUpdated 30w ago
Repository

About cohort-analysis

cohort-analysis is a framework skill for comparing performance across defined groups and diagnosing differences over time. It combines metric selection, normalization, visualizations, and narrative guidance for analysis and forecasting.

Key features

  1. 01Define cohorts and inclusion rules
  2. 02Select cohort-level KPIs
  3. 03Normalize for mix and seasonality
  4. 04Visualize divergence across cohorts
  5. 05Annotate drivers and actions

Use cases

  1. 01Compare acquisition channels or segments
  2. 02Diagnose conversion drops by cohort
  3. 03Test forecasts against historical behavior

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gtmagents/gtm-agents --skill cohort-analysis

After installing, type/cohort-analysisin Claude Code to confirm it loaded.

Details

From the project README

Cohort Analysis Framework Skill

When to Use

  • Comparing performance across acquisition channels, segments, or product lines.
  • Diagnosing conversion drop-offs within specific booking/vintage cohorts.
  • Stress-testing forecast assumptions with historical baseline behavior.

Framework

  1. Cohort Definition – choose cohort key (signup month, lead source, product tier, segment).
  2. Metric Stack – select KPIs (coverage, win rate, ACV, NRR, payback) per cohort.
  3. Normalization – adjust for seasonality, deal size mix, or currency.
  4. Visualization – waterfall tables, heatmaps, or overlapping curves to highlight divergence.
  5. Narrative Layer – annotate drivers, anomalies, and recommended actions.

Templates

  • Cohort definition worksheet (keys, filters, inclusion/exclusion rules).
  • Standardized chart pack for leadership readouts.
  • Diagnostic checklist for follow-up analyses.

Tips

  • Keep cohorts mutually exclusive to avoid double-counting.
  • Pair with inspect-pipeline-levers to link cohort insights to pipeline stages.
  • Rebaseline quarterly so assumptions stay current.

Comments

Markdown supported