An intelligent data processing skill that automates financial customer clustering, feature extraction, and visual reporting from CSV or Excel files.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install customer-segment
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install customer-segment using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Customer Segmentation Skill?
The Customer Segmentation skill is a specialized tool designed for financial institutions and data analysts to categorize their client base effectively. By leveraging Openclaw Skills, this tool automates the heavy lifting of data cleaning, feature engineering, and machine learning, allowing users to move from raw transaction logs to actionable business intelligence in seconds.
It utilizes advanced statistical methods to identify patterns in customer behavior, assets, and engagement levels. This ensures that marketing teams and financial advisors can provide personalized services to high-value VIPs while identifying at-risk customers who may be nearing churn.
Customer Segmentation Skill Use Cases
- Analyzing bank customer data to identify high-net-worth VIP individuals.
- Identifying potential growth customers based on recent transaction frequency and rising asset balances.
- Detecting dormant or churn-risk customers for re-engagement marketing campaigns.
- Generating automated visual reports for stakeholder presentations based on raw CSV/Excel uploads.
How Customer Segmentation Skill Works
- Data Ingestion: The skill triggers when a user uploads a CSV or Excel file containing transaction, asset, or behavioral data.
- Automated Cleaning: It identifies core fields like customer_id, balance, and txn_amount, while handling missing values through median or mode imputation.
- Feature Engineering: The system constructs an RFM (Recency, Frequency, Monetary) model combined with product depth and customer tenure.
- K-Means Clustering: It applies the Elbow Method to determine the optimal number of segments (K) or defaults to a high-to-low value 5-tier system.
- Visualization: Generates comparative charts, including radar maps and heatmaps, to illustrate the differences between customer clusters.
- Report Export: Produces a comprehensive package including labeled CSVs, summary statistics, and a Markdown analysis report.
Customer Segmentation Skill Setup
To use this skill within your Openclaw Skills environment, ensure you have the necessary Python data science stack installed:
pip install pandas sklearn matplotlib seaborn
Once installed, place your customer data files in the monitored directory or upload them directly to the agent interface. The skill will automatically activate when it detects relevant financial headers or when prompted with phrases like "analyze customers."
Customer Segmentation Skill Data Schema & Taxonomy
The skill organizes its output into a structured format to ensure clarity and portability:
| File Name | Description | Format |
|---|---|---|
segmentation_results.csv |
Full list of customers with assigned clusters and labels. | CSV |
cluster_summary.csv |
Statistical averages (Mean/Median) for each identified group. | CSV |
segmentation_charts.png |
Combined visualization dashboard (Radar, Heatmap, Histogram). | PNG |
segmentation_report.md |
Executive summary and actionable business insights. | Markdown |
Customer Segmentation Skill Advanced Features
- Intelligent Column Mapping: Automatically maps localized headers (e.g., "客户ID") to standardized technical fields.
- Dynamic K-Selection: Uses the SSE elbow method to automatically find the most statistically significant number of clusters.
- Multi-Dimensional Tagging: Assigns semantic labels such as VIP, Potential, Stable, Active, and Churn-Alert based on cluster centroids.
- High-Fidelity Visualization: Uses Matplotlib and Seaborn with specialized font support for multilingual reporting.
SKILL.md
Loading
Related Openclaw Skills
SOC 2 Readiness Checker
A comprehensive compliance assessment tool that evaluates organizational control posture against SOC 2 Trust Services Criteria.
Litigation Response Strategy
A sophisticated AI tool designed to parse legal complaints, identify core legal relationships, and formulate actionable litigation defense strategies.
Feishu Work Review Timemachine
An AI-powered analytical tool that synthesizes Feishu activity into high-signal weekly or monthly work retrospectives.
OpenMath Submit Theorem
A professional-grade blockchain submission skill for committing and revealing formal mathematical proofs on the Shentu network.
Sakura: Recursive Fractal Art & Animation
A creative Python-based skill that uses recursive algorithms to draw artistic cherry blossom trees with dynamic falling petal effects.
Deep Research
An advanced two-phase research agent that collaborates on structured investigation plans before executing autonomous multi-source data gathering and synthesis.
Featured*
