Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Customer Analytics & RFM Segmentation

    1

    Analyze customer transactions, identify valuable customer segments using RFM, calculate revenue KPIs, and generate actionable marketing and retention recommendations.

    Free

    Security scanned
    Customer Analytics & RFM Segmentation

    Customer Analytics & RFM Segmentation

    Example session with this skill installed

    Analyze my customer transactions CSV. Calculate total revenue, average order value, customer RFM scores, and customer segments. Identify high-value customers and recommend targeted marketing and retention actions.

    • Read your context and instructions
    • Compiled the customer analytics
    • Generated the data export

    Customer Analytics Report — Synthetic Demo

    Executive Summary

    Analyzed 12 transactions from 9 customers, covering August 17 to November 5, 2026. Total observed revenue was 885 currency units, with an average order value of 73.75.

    RFM Segments

    SegmentCustomersCustomer ShareRevenue Share
    Champions333.33%54.24%
    New / Promising111.11%22.60%
    Other555.56%23.16%

    Key Findings

    • Three Champions account for more than half of total observed revenue.
    • One New / Promising customer contributes 22.60% of observed revenue.
    • Other customers represent most of the customer base but generate less than a quarter of revenue.

    Recommendations

    1. Champions: Test loyalty rewards and referral campaigns. Track repeat purchase rate and incremental revenue against a randomized control group.
    2. New / Promising: Test onboarding and second-purchase messages to encourage repeat transactions.
    3. Other: Review order history and customer context before choosing a retention strategy.

    Files Produced

    • summary.json
    • customer_segments.csv
    • segment_summary.csv
    • report.md

    Methodological Notes

    RFM scores are descriptive percentile-based measures. Segments follow predefined rules. The demo does not establish causal effects, future purchase probability, or campaign ROI. All observations are synthetic.

    customer_segments.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Customer Analytics & RFM Segmentation

    Turn raw customer transaction data into actionable business intelligence.

    This skill helps marketing teams, business analysts, entrepreneurs, and data professionals understand customer purchasing behavior and identify opportunities to improve retention and customer engagement.

    What it does

    • Customer segmentation: Classifies customers using Recency, Frequency, and Monetary (RFM) analysis.
    • Revenue analytics: Calculates total revenue, average order value, purchasing frequency, and revenue contribution by segment.
    • Customer behavior: Identifies high-value, loyal, at-risk, and promising customer groups.
    • Marketing recommendations: Suggests targeted retention, loyalty, onboarding, and customer reactivation strategies.
    • Reproducible reporting: Generates structured summaries and customer segmentation outputs using Python.

    How it works

    Provide a CSV dataset containing customer IDs, transaction IDs, dates, and transaction values. The skill validates the input, calculates RFM scores, segments customers, and creates a report with practical recommendations.

    Ideal for

    E-commerce businesses, marketing analysts, CRM teams, data analysts, and small businesses looking to understand customer value.

    Important

    This version uses interpretable RFM scoring rather than K-means clustering. It runs locally on user-provided data without requiring external APIs. Its recommendations are descriptive and should be validated through controlled experiments before being treated as proven marketing outcomes.

    Requires Python 3.10+ and pandas. Uses rule-based heuristics rather than machine learning clustering. Cannot predict future churn or calculate ROI without cost data.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Requires

    Python
    pandas

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listedtoday

    What's inside

    Frequently Asked Questions

    You need a CSV file with four specific columns: `customer_id`, `order_id`, `order_date`, and `revenue`. The skill is flexible; if your headers use different names, it will prompt you to map them before starting the analysis.

    Unlike standard AI prompts that might guess at numbers, this skill uses a local Python script and the `pandas` library to perform exact percentile calculations. This ensures your segments are based on auditable math rather than LLM intuition, providing reliable results for large datasets.

    The skill operates entirely on your local machine, using a local Python environment to process your CSV. No transaction-level data is sent to external APIs, ensuring your customer purchase history remains private and secure.

    This skill requires Python 3.10+ and the `pandas` library installed in your agent's environment. It is designed to work with AI agents that have local file system access and the ability to execute Python scripts.

    You will receive the core analytical script, the AI agent configuration files, and a guide for setup. This includes the logic for data validation, RFM scoring, and the heuristic rules used to categorize customers into segments like "Champions" or "At Risk."

    The skill identifies "At Risk" customers who haven't purchased recently, allowing you to export those IDs for targeted win-back email campaigns. It also highlights "Champions" for loyalty rewards, helping you prioritize marketing spend where it has the highest impact.

    New in Marketing & SEO