Mmcp.market

cohort-analysis-specialist skill

by florianbonnet14·florianbonnet14/ThePowerOfAnalytics_ClaudeSkills·29 stars·MIT

Track customer behavior over time by grouping customers based on shared characteristics or experiences. Use when measuring retention rates, understanding how customers evolve over time, comparing new vs old user behavior, evaluating product changes by cohort, identifying at-risk cohorts early, or calculating LTV by cohort. Essential for understanding retention, lifecycle patterns, and how product changes affect different user vintages.

A100/100content scan

Is the cohort-analysis-specialist skill safe?

Clean: nothing in its files matched our rules. We read 3 files in the folder on 2026-09-28.

No findings.

Install the cohort-analysis-specialist skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/florianbonnet14/ThePowerOfAnalytics_ClaudeSkills.git /tmp/ThePowerOfAnalytics_ClaudeSkills
mkdir -p ~/.claude/skills
cp -r /tmp/ThePowerOfAnalytics_ClaudeSkills/cohort-analysis-specialist ~/.claude/skills/cohort-analysis-specialist
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Cohort Analysis Specialist

Track customer behavior over time by grouping customers into cohorts for temporal analysis. Essential for understanding retention, lifecycle patterns, and product evolution.

Core Framework: Understanding Cohorts

What is a Cohort?

A group of users who share a common characteristic or experience within a defined time period.

Most common: Acquisition cohort (when they signed up)

Why Cohorts Matter: Overall metrics can hide important trends. Example:

  • Overall retention: 60%
  • But actually: 2023 cohorts 75%, 2024 cohorts 45%
  • Without cohorts, you wouldn't know new users perform worse!

Cohort Types

Type 1: Acquisition Cohorts

Definition: Grouped by signup/first purchase date

Time granularity:

  • Daily (high volume, short analysis)
  • Weekly (most common, balances detail/manageability)
  • Monthly (strategic analysis, lower volume)
  • Quarterly (very long-term trends)

Best for: Retention analysis, lifecycle understanding, LTV calculation

Type 2: Behavioral Cohorts

Definition: Grouped by specific action

Examples: Activated cohort, Converters, Feature adopters, Engagement level

Best for: Feature impact analysis, engagement optimization

Type 3: Attribute Cohorts

Definition: Grouped by characteristic at acquisition

Examples: Acquisition channel, Plan tier, Geographic, Segment

Best for: Channel quality, segment performance, market analysis

Key Analysis: The Retention Table

Classic Cohort Retention Table

Structure:

M0   M1   M2   M3   M4   M5   M6
Jan 24   100% 65%  52%  45%  41%  38%  36%
Feb 24   100% 68%  55%  48%  44%  40%  38%
Mar 24   100% 70%  58%  51%  46%  42%  --
Apr 24   100% 72%  60%  53%  48%  --   --
May 24   100% 74%  62%  55%  --   --   --
Jun 24   100% 75%  63%  --   --   --   --
Jul 24   100% 76%  --   --   --   --   --

How to read:

  • Rows: Each cohort (signup month)
  • Columns: Time since signup
  • Cells: % of original cohort still active
  • M0: Always 100%
  • Diagonal: Most recent data

Key insights:

  1. Vertical: Compare same period across cohorts (M1 improving: 65%→76%)
  2. Horizontal: See retention curve shape (steep drop early, then gradual)
  3. Trends: Draw lines through columns to see improvement/decline

Building a Retention Table (Descriptive)

Data to Collect:

  • User signup dates grouped into cohorts (weekly or monthly)
  • Activity data for each user in each subsequent period
  • Definition of "active" (logged in, made purchase, used core feature)
  • Time periods to track (typically 6-12 months)

How to Analyze:

Analysis 1: Create Retention Table

  • Format: Table with cohorts as rows, time periods as columns
  • Calculate: For each cohort and period, % of original cohort active
  • Color coding: Use heat map (red <40%, orange 40-60%, yellow 60-75%, green >75%)
  • Mark: Incomplete data (recent cohorts) clearly

Analysis 2: Cohort Retention Curves

  • Chart type: Line chart
  • X-axis: Time periods (M0, M1, M2, etc.)
  • Y-axis: Retention rate (%)
  • Lines: One line per cohort
  • Look for: Separation between cohorts, curve shapes

Analysis 3: Period-Specific Trends

  • Chart type: Line chart showing trends over time
  • X-axis: Cohort (chronological)
  • Y-axis: Retention rate
  • Lines: Separate line for M1, M2, M3 retention
  • Look for: Improvement or decline in specific periods

What to Look For:

Good patterns:

  • Recent cohorts performing better than old (product improving)
  • Curves plateau after M3-M6 (stable long-term retention)
  • M1 retention >40%, M3 retention >30%

Bad patterns:

  • Recent cohorts worse than old (product degrading)
  • No plateau, continuous decline (no loyal base forming)
  • Steep early drop that never recovers

Key Metrics from Cohort Analysis

D1/D7/D30 Retention

Definition: % active on specific day after signup

Milestones:

  • D1 (Next Day): Immediate value delivery (target >40%)
  • D7 (Week 1): Habit formation (target >30%)
  • D30 (Month 1): Product stickiness (target >20%)

Analysis:

  • Compare D1/D7/D30 across cohorts
  • Track trends over time
  • Identify which milestone is weakening

Retention Curve Shape Analysis

Question: How does retention decay over time?

Patterns:

  • Smiling curve: Dip then recovery (common in B2B, slow onboarding)
  • Flat after dip: Initial drop then stable (good pattern)
  • Continuous decline: No stickiness, churn risk
  • Plateau: Healthy engaged user base

Cohort Lifetime Value (LTV)

Calculate: Revenue per cohort over lifetime

Analysis:

  • Compare LTV across cohorts (improving or declining?)
  • Calculate time to 80% of LTV (payback period)
  • Segment LTV (by channel, segment, etc.)

More skills from florianbonnet14/ThePowerOfAnalytics_ClaudeSkills

  • Aanalysis-plannerStructure analysis investigations before diving into data, preventing wasted time and ensuring thoroughness. Use when users need to plan any significant analysis, investigate KPI changes, respond to stakeholder questions, plan feature/experiment analysis, or when previous analyses were unfocused. Helps define clear goals, generate testable hypotheses, create systematic analysis roadmaps, identify required data, estimate timelines, and prevent analysis paralysis.
  • Aanalysis-results-collectorTransform completed analysis work into structured, communication-ready documentation by conducting guided conversations that extract key findings, evidence, and recommendations. Use when a user has completed an analysis (typically following an analysis plan created by the analysis-planner skill) and needs to document results, create findings summaries, build executive reports, or prepare analysis outcomes for stakeholder communication. This skill systematically gathers what was tested, what was found, and what should be done next, then generates a professional markdown document ready for distribution.
  • Aanalytics-orchestratorIntelligent entry point to the analytics ecosystem based on "The Power of Analytics" book by Florian Bonnet. Guides users to the right analytics agent based on their needs, recommends workflow sequences, and provides clear instructions for launching agents. Use when users need help choosing between analytics agents, want to start an analytics project but aren't sure where to begin, or ask "what can you help me with" in an analytics context. Also use when users mention analytics tasks like defining metrics, planning analysis, collecting results, creating presentations, or writing executive summaries.
  • Aexecutive-summary-writerTransform analysis findings into clear, actionable executive summaries using the MAIN framework (Motive, Answer, Impact, Next steps) and Pyramidal Principle. Use when completing any analysis that needs stakeholder buy-in, preparing for leadership meetings, documenting investigation findings, writing business reviews, creating post-mortems, proposing initiatives based on data, or communicating insights to executives.
  • Ainfluential-factors-detectiveIdentify and analyze qualitative factors that influence KPIs but can't be measured as numbers. Use when users need to find non-quantifiable drivers affecting metrics (like copy quality, design aesthetics, timing), plan A/B tests for subjective elements, bridge the gap between data and design/content decisions, understand why quantitative analysis is incomplete, optimize messaging or UX elements, or identify the actual levers to pull for improving KPIs at the leaf nodes of a KPI tree.
  • Akpi-tree-architectBuild comprehensive KPI trees from North Star metrics. Use when users need to decompose metrics into hierarchical driver structures, create MECE (Mutually Exclusive, Collectively Exhaustive) breakdowns, identify leverage points, map performance drivers, or prepare for root cause analysis. Essential for setting up analytical foundations after defining a North Star metric.
  • Anorth-star-metric-advisorStrategic framing and KPI setting specialist that helps identify and validate the single most important metric capturing customer value delivery and predicting business success. Use when starting a new team or product, when existing product lacks clear success metric, when team seeks to define what success means, or when metrics don't align with customer value and/or business goals.
  • Apresentation-builderTransform analysis documents into structured presentation slide plans. Use when users need to convert markdown analysis documents into presentation decks, create slide-by-slide breakdowns with specific slide types and content structure, or plan presentation flow from analytical content. Outputs detailed slide specifications including slide types (Cover, Executive Summary, Text, Chart, Section) and all required content elements for each slide.
  • Asegmentation-expertIdentify, analyze, and act on customer segments to uncover hidden patterns and understand behavior differences. Use when investigating KPI changes to understand which customers drove them, planning targeted initiatives, building customer personas, or analyzing performance differences across groups. Helps select meaningful segmentation dimensions, create actionable segments, analyze performance differences, calculate segment contributions, and generate segment-specific recommendations.

All agent skills → · MCP servers