exploratory-data-analysis
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.
Author
Category
Development ToolsInstall
Download and extract to your skills directory
Copy command and send to AI Agent for auto-install:
Exploratory Data Analysis — Scientific Data Exploration and Analysis
Skill Overview
Exploratory Data Analysis is an automated data analysis skill designed specifically for researchers. It supports more than 200 scientific file formats, automatically detects file types, and generates detailed reports containing format-specific analyses, quality assessments, and recommendations for downstream analyses.
Use Cases
1. Rapid Exploration of Scientific Data Across Multiple Fields
When you receive an unfamiliar scientific data file and need to quickly understand its structure and contents, this skill can automatically identify the file format—whether it is a bioinformatics FASTQ file, a PDB file containing chemical molecular structures, an ND2 microscopy image, or an mzML spectroscopy file—and provide targeted analyses, allowing you to understand the characteristics of the data without having to consult extensive documentation.
2. Data Quality Assessment and Validation
Before conducting formal analyses, you need to verify the completeness and quality of your data. This skill performs comprehensive quality checks, including missing-value detection, outlier identification, and statistical distribution analysis, helping you identify potential data issues in a timely manner and avoid wasting time in subsequent analyses.
3. Analysis Method Selection and Planning
When faced with a new dataset, are you unsure what type of analysis method to use? Based on the file type and data characteristics, this skill provides specific recommendations for downstream analyses, visualization approaches, and tools, helping you quickly develop an appropriate analysis strategy.
Core Features
1. Intelligent File Format Detection
Automatically identifies more than 200 scientific file formats across six major fields: chemical and molecular formats (60+ extensions), bioinformatics and genomics (50+ extensions), microscopy and imaging (45+ extensions), spectroscopy and analytical chemistry (35+ extensions), proteomics and metabolomics (30+ extensions), and general scientific data formats (30+ extensions).
2. Format-Specific In-Depth Analysis
Automatically selects the most appropriate analysis method based on the file type. For sequence files (FASTQ/FASTA), it analyzes length distributions and GC content; for structure files (PDB/CIF), it checks molecular geometry and quality; for image files (ND2/CZI), it extracts dimensional information and intensity statistics; and for tabular data (CSV/Excel), it calculates correlations and identifies outliers.
3. Automatic Analysis Report Generation
Generates a detailed Markdown-formatted analysis report with one click. The report includes basic file information, data structure, statistical summaries, quality metrics, visualization recommendations, and proposed next steps for analysis, making it easy to save, share, or include as part of project documentation.
Frequently Asked Questions
What file formats does this skill support?
It supports more than 200 scientific data file formats, including but not limited to: FASTA, FASTQ, SAM, BAM, and VCF in bioinformatics; PDB, CIF, MOL, and SDF in chemistry; TIFF, ND2, CZI, and LIF for microscopy images; mzML, mzXML, and RAW in spectroscopy; as well as general formats such as CSV, HDF5, and NPY. For the complete list of supported formats, refer to the reference files in the skill documentation.
How do I use this skill to analyze my data?
Simply provide the file path, and the skill will automatically complete the entire analysis. You can run scripts/eda_analyzer.py <your-file-path> directly. The skill will automatically detect the file type, load the corresponding analysis strategy, perform the analysis, and generate a Markdown report. For complex analytical requirements, the skill also supports customized in-depth analysis through conversation.
What can the analysis report tell me?
The report provides comprehensive information about your data: file type and basic attributes, data dimensions and structure, statistical summaries (mean, standard deviation, quantiles, etc.), data quality assessments (missing values, outliers, and duplicate entries), and specific analysis recommendations based on the data type (such as whether standardization is needed, recommended visualization methods, and suitable downstream analysis methods). This information can help you quickly determine whether the data is suitable for your analytical needs and how it should be processed.