An automated data analysis skill that parses CSV, Excel, and JSON files to perform descriptive statistics, detect anomalies, analyze trends, and suggest data visualizations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install zcx-data-analyzer
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 zcx-data-analyzer 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 Data Analyzer?
The Data Analyzer skill is a comprehensive utility designed for AI agents to load, profile, analyze, and report on structured datasets. By integrating this capability, your agent can process standard file formats like CSV, Excel, JSON, and TSV, turning raw files into highly structured statistical summaries and detailed data-driven reports. It is one of the essential Openclaw Skills built to offload heavy lifting in data preparation and exploratory data analysis (EDA).
Using either Python-based libraries (like Pandas and Openpyxl) or fallback native parsing techniques, this tool automatically extracts key column parameters, uncovers data quality issues (such as missing values), and determines distributions. This ensures your agent handles structured data intelligently, establishing a robust pipeline from raw input to visual and structural recommendations.
Data Analyzer Use Cases
- When an agent needs to perform exploratory data analysis (EDA) on a newly provided CSV or Excel dataset.
- To automatically clean data by profiling column shapes, identifying missing cells, and finding structural anomalies using IQR or Z-Score techniques.
- Generating professional data analysis reports containing trend lines, correlation coefficients (Pearson r), and tailored chart recommendations.
- Offloading manual statistics calculations (such as skewness, standard deviation, and percentiles) to automated script execution within Openclaw Skills pipelines.
How Data Analyzer Works
- Data Loading & Formats: The agent reads the input file (CSV, Excel, JSON, or TSV), inspects its shape, resolves delimiters, and identifies schema attributes such as column types and unique counts.
- Profile & Statistics Calculation: It computes basic descriptive statistics including mean, median, standard deviation, and percentiles for numeric data, alongside top frequency metrics for categorical fields.
- Deep Analysis: It runs correlation matrices to evaluate linear relationships and applies outlier detection methods (like the 1.5 * IQR fence or Z-Score thresholding) to catch data anomalies.
- Trend Mapping: For time-series data, it aggregates records by timeframes (day/week/month) to track directional growth, rates of change, or seasonality.
- Report & Visualization Generation: The skill outputs a comprehensive markdown report complete with data insights and recommendations for the best visual charts (such as histograms, scatter plots, or box plots) to use.
Data Analyzer Setup
Enable the Data Analyzer skill within your environment and install the required dependencies:
# Install pandas and openpyxl for Excel and advanced CSV support
pip install pandas openpyxl
To verify your system configuration or run manual analysis diagnostics:
python3 -c "
import pandas as pd
df = pd.read_csv('data.csv')
print(df.info())
print(df.describe())
print(df.head())
"
Data Analyzer Data Schema & Taxonomy
The Data Analyzer skill handles file ingestion and reports using the following schema specifications:
| Input Type | Parsing Mechanics | Output Format |
|---|---|---|
| CSV / TSV | Delimiter parsed, header mapped, data rows converted to arrays | Structured Python Dict or Pandas DataFrame |
| Excel (.xlsx) | Read sheet-by-sheet using openpyxl, auto-converting to flat tables | DataFrames with active sheet tracking |
| JSON | Flattened nested structures to extract objects and arrays | Normalized key-value records |
When generating full markdown reports, the structured output follows this taxonomy:
- Overview: Dimensions (Rows x Cols), missing data ratio (%), and schema types.
- Descriptive Statistics: Numeric table (
count,mean,median,std,min,25%,75%,max) and Categorical table (count,unique,top,frequency). - Key Findings: Metric breakdowns coupled with recommended chart visualizations (e.g., histograms, scatter plots, bar charts).
- Anomalies Table: Identified rows showing column name, value, and deviation severity.
- Correlations: Paired variables with a Pearson
rvalue greater than|0.3|.
Data Analyzer Advanced Features
- Multi-Method Outlier Detection: Seamlessly switches between Interquartile Range (IQR) for skewed data and Z-Score thresholding for normally distributed inputs to detect anomalies.
- Intelligent Chart Recommendations: Matches specific findings with optimal visual formats (like box plots for distributions, heatmaps for correlations, and line charts for temporal trends).
- Custom Python Script Fallbacks: Generates standalone, self-contained Python analysis scripts (
analysis.py) for offline, memory-efficient processing of extremely large datasets. - Integrated Openclaw Skills workflows: Chains easily with automated reporting, email delivery, or database-writing agents to construct complex data-processing pipelines.
SKILL.md
Loading
Related Openclaw Skills
Daily Market Report
An AI-powered skill to automatically compile, analyze, and generate professional daily market reports for Chinese commodity and financial futures.
Fridge Chef
An AI-powered culinary assistant that identifies ingredients from fridge photos to recommend personalized, low-waste recipes.
Meeting Notes Skill
An AI agent skill that transforms raw meeting transcripts, summaries, or shorthand notes into highly structured, actionable meeting minutes.
SIFF 2026 Ticket & Itinerary Planner
An advanced spatiotemporal scheduling agent that builds perfect film festival itineraries using OSRM driving matrices, metro networks, and custom post-screening buffers.
Economic Calendar
Track and analyze global economic data releases, central bank meetings, and key financial events to build actionable trading strategies.
ScholarPlot Skill
ScholarPlot is an AI-powered academic figure generation skill that connects to MCP to instantly create and edit SCI-journal standard figures from natural language.
Featured*
