domains / families / data / exploratory-data-analysis

exploratory-data-analysis

combined

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed. 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 generate...

When to use

• User provides a path to a scientific data file for analysis
• User asks to "explore", "analyze", or "summarize" a data file
• User wants to understand the structure and content of scientific data
• User needs a comprehensive report of a dataset before analysis
• User wants to assess data quality or completeness
• User asks what type of analysis is appropriate for a file

When not to use

• certifying a file
• inferring scientific meaning
• confirmatory, clinical, mechanistic, or causal claims
• reading URLs, pipes, stdin, generic archives, symlinks
• using pickle/joblib/dill or dynamic evaluation
• printing raw rows, sequences, or direct identifiers
• automatically deleting outliers, filtering, imputing, or transforming raw data
• unknown formats

Skill page

Conflict

The K-Dense-AI copy is a hardened, bounded, security-focused EDA skill with a strict capability matrix, safe I/O contract, and fail-closed behavior for unsupported formats. The other three copies (zLanqing, foryourhealth111-pixel, aipoch) are near-identical, broader-scope skills that promise 200+ format coverage, reference-file lookups, and a general-purpose analyzer script. They disagree on scope, safety constraints, and execution model, so crowning one would hide a real alternative.