Mmcp.market

segmentation-expert skill

by florianbonnet14·florianbonnet14/ThePowerOfAnalytics_ClaudeSkills·29 stars·MIT

Identify, 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.

A100/100content scan

Is the segmentation-expert 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 segmentation-expert 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/segmentation-expert ~/.claude/skills/segmentation-expert
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

Segmentation Expert

Identify and analyze customer segments to uncover hidden patterns, understand behavior differences, and tailor strategies for maximum impact.

Core Framework: The Segmentation Process

Phase 1: Define Segmentation Dimensions

Main Dimension Categories:

1. Demographic (B2C: age, gender, location; B2B: company size, industry, funding stage) 2. Behavioral (usage level, feature adoption, session frequency, purchase patterns) 3. Acquisition (channel, campaign, referrer, first touchpoint) 4. Lifecycle (tenure, cohort, stage, product tier, upgrade history) 5. Psychographic (job to be done, use case, goals, pain points) 6. Firmographic (B2B: industry, revenue, employee count, tech stack)

Phase 2: Select Relevant Dimensions

Selection Criteria (Score 1-5 each):

  1. Actionability: Can you do something different for this segment?
  2. Measurability: Can you identify segment membership easily?
  3. Size/Viability: Is segment large enough (typically >5%)?
  4. Stability: Does definition remain consistent over time?
  5. Differentiation: Do segments behave differently (>20% performance difference)?

Selection Process:

  1. Brainstorm all possible dimensions (10-20)
  2. Score each on 5 criteria (max 25 points)
  3. Select top 3-5 dimensions (score >15/25)
  4. Validate with data (check if differences exist)

Phase 3: Create Segments

Methods:

Rules-Based: Explicit rules define membership

  • Example: "Power Users = >20 sessions/month AND use >5 features"
  • Best for: Operational segmentation, clear behavioral groups

Value-Based: Segment by value delivered/generated

  • Example: "High-Value = Top 20% by LTV"
  • Best for: Prioritization, resource allocation

RFM (Recency, Frequency, Monetary): Classic for transaction businesses

  • Champions: Recent, Frequent, High-Value
  • At-Risk: Previously high-value, now less recent
  • Best for: E-commerce, SaaS with usage tiers

Clustering (Statistical): Algorithm finds natural groupings

  • K-means, hierarchical clustering, DBSCAN
  • Best for: Exploratory analysis, persona development

Persona-Based: Segments based on goals, use cases, JTBD

  • Best for: Product strategy, positioning

Phase 4: Analyze Segment Performance

For each segment, describe analysis in words:

Data to Collect:

  • Segment size (number of users, % of total)
  • Key metrics per segment (conversion, retention, engagement, LTV)
  • Time trends for each segment
  • Overlap with other segmentation dimensions

How to Analyze:

Analysis 1: Segment Size and Composition

  • Chart type: Pie chart or stacked bar
  • Show: % of total users or revenue per segment
  • Compare: Current period vs previous period

Analysis 2: Performance Comparison

  • Chart type: Grouped bar chart or comparison table
  • X-axis: Segments
  • Y-axis: Key metric (conversion rate, LTV, retention, etc.)
  • Show: Performance difference between segments
  • Highlight: Best and worst performing segments

Analysis 3: Trend Over Time

  • Chart type: Multi-line chart
  • X-axis: Time (weeks or months)
  • Y-axis: Key metric
  • Lines: One line per segment
  • Look for: Divergence or convergence of segments

What to Look For:

Segment differences:

  • Which segments perform significantly better/worse (>20% difference)?
  • Is the difference consistent over time?
  • Are differences statistically significant?

Segment contribution:

  • Which segments drive most of the overall metric change?
  • Calculate contribution: (Segment size × Performance difference)

Actionable patterns:

  • What characteristics define high-performing segments?
  • Can low-performing segments be improved or high-performing ones scaled?

Phase 5: Generate Recommendations

Framework:

For each segment, specify:

  • Current Performance: What metrics show
  • Root Cause: Why this segment performs this way
  • Opportunity: What could be improved
  • Action: Specific, testable intervention
  • Expected Impact: Quantified improvement estimate
  • Priority: Based on impact × feasibility

Segmentation Patterns

Pattern 1: Acquisition Channel Segmentation

Use when: Understanding marketing effectiveness

Dimensions: Organic, Paid, Referral, Partnership, Direct

Analysis approach:

  • Compare conversion, retention, LTV by channel
  • Calculate CAC and payback period by channel
  • Identify highest quality channels

Pattern 2: Usage Level Segmentation

Use when: Understanding engagement

Dimensions: Power Users, Regular Users, Casual Users, Inactive

Rules example:

  • Power: >20 sessions/month
  • Regular: 10-20 sessions/month
  • Casual: 1-9 sessions/month
  • Inactive: 0 sessions/month

Analysis approach:

  • Track distribution over time
  • Analyze migration between segments
  • Identify "aha moment" that moves users up

Pattern 3: Lifecycle Stage Segmentation

Use when: Optimizing customer journey

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.
  • Acohort-analysis-specialistTrack 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.
  • 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.

All agent skills → · MCP servers