Skills exploratory-data-analysis

📦

exploratory-data-analysis

Name: exploratory-data-analysis
Author: davila7

Content revision r1 Safe 📁 Filesystem access⚙️ External commands

Analyze Scientific Data Files

Scientific datasets often arrive in specialized formats that are hard to inspect quickly. This skill detects the format, summarizes contents, checks quality, and produces a clear EDA report.

Supports: Claude Codex Code(CC)

🥇 85 Gold

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "exploratory-data-analysis" from https://skillstore.io/skills/davila7-exploratory-data-analysis.md and its manifest at https://skillstore.io/api/skills/davila7-exploratory-data-analysis/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-exploratory-data-analysis.md Signed manifest GET /api/skills/davila7-exploratory-data-analysis/manifest Signed lockfile GET /api/skills/davila7-exploratory-data-analysis/lockfile

Test it

Using "exploratory-data-analysis". Analyze reads.fastq for basic quality and structure.

Expected outcome:

A markdown report describing FASTQ format, sampled read count, length range, mean quality, GC-related recommendations, and next quality-control steps.

Using "exploratory-data-analysis". Explore experiment_results.csv and identify data quality issues.

Expected outcome:

A tabular EDA summary with row and column counts, inferred data types, missing-value counts, numeric summaries, and suggested cleaning steps.

Using "exploratory-data-analysis". Review cells.tif before image analysis.

Expected outcome:

An imaging report with dimensions, mode, value range, page count when available, and recommendations for segmentation and intensity normalization.

Security Audit

Safe

v13 • 7/9/2026 Open versioned report

The static findings are false positives caused by scientific terminology, markdown code formatting, and legitimate local file analysis behavior. The analyzer reads user-provided local scientific data, extracts metadata and summaries, and writes a markdown report; no shell execution, network reconnaissance, credential access, prompt injection, or malicious intent was found.

Files scanned

4,808

Lines analyzed

Review items

False positives ignored

Risk Factors

📁 Filesystem access (9)

references/general_scientific_formats.md:13 references/general_scientific_formats.md:233 references/general_scientific_formats.md:248 references/microscopy_imaging_formats.md:121 references/microscopy_imaging_formats.md:448 references/microscopy_imaging_formats.md:516 references/proteomics_metabolomics_formats.md:178 scripts/eda_analyzer.py:508 SKILL.md:374

⚙️ External commands (50)

scripts/eda_analyzer.py:440 scripts/eda_analyzer.py:441 scripts/eda_analyzer.py:444 scripts/eda_analyzer.py:470-472 scripts/eda_analyzer.py:472-476 SKILL.md:38 SKILL.md:40 SKILL.md:45 SKILL.md:47 SKILL.md:52 SKILL.md:54 SKILL.md:59 SKILL.md:61 SKILL.md:66 SKILL.md:68 SKILL.md:73 SKILL.md:75 SKILL.md:89-95 SKILL.md:95-105 SKILL.md:105-109 SKILL.md:109-112 SKILL.md:112-120 SKILL.md:120-188 SKILL.md:188-193 SKILL.md:193-194 SKILL.md:194 SKILL.md:215-221 SKILL.md:221 SKILL.md:222 SKILL.md:228-237 SKILL.md:237-243 SKILL.md:243-267 SKILL.md:267-286 SKILL.md:286-290 SKILL.md:290-310 SKILL.md:310-314 SKILL.md:314-335 SKILL.md:335-346 SKILL.md:346-351 SKILL.md:351-354 SKILL.md:354 SKILL.md:355 SKILL.md:356 SKILL.md:357 SKILL.md:358 SKILL.md:380-382 SKILL.md:382-394 SKILL.md:394-429 SKILL.md:429-432 SKILL.md:432-433

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: claude View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-exploratory-data-analysis/audits/13?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-exploratory-data-analysis/security.svg)](https://skillstore.io/skills/davila7-exploratory-data-analysis?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-exploratory-data-analysis?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-exploratory-data-analysis/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-exploratory-data-analysis.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). exploratory-data-analysis security audit report (audit version 13) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-exploratory-data-analysis/audits/13

BibTeX citation

@techreport{davila7-davila7-exploratory-data-analysis-2026,
  author = {davila7},
  title = {exploratory-data-analysis security audit report (audit version 13)},
  institution = {Skillstore},
  year = {2026},
  number = {13},
  url = {https://skillstore.io/skills/davila7-exploratory-data-analysis/audits/13},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "exploratory-data-analysis security audit report (audit version 13)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/davila7-exploratory-data-analysis/audits/13"
identifiers:
  - type: other
    value: "skillstore:davila7-exploratory-data-analysis:audit:13"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended Current

davila7-exploratory-data-analysis

Skillstore Score 85

Evidence Confidence High

Skillstore usage 58

Updated

2026-08-21

K-Dense-AI

k-dense-ai-exploratory-data-analysis

Skillstore Score 76

Evidence Confidence High

Skillstore usage 38

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Inspect a new sequencing dataset

Identify FASTA or FASTQ structure, summarize sequence counts and lengths, and recommend quality-control steps.

Review microscopy image metadata

Summarize image dimensions, channels, value ranges, and downstream image-analysis recommendations.

Profile a general experiment table

Load CSV or TSV files, inspect columns, missing values, data types, and basic numerical summaries.

Try These Prompts

Analyze one data file

Analyze this scientific data file and create an exploratory data analysis summary: <path-to-file>.

Assess data quality

Run an EDA pass on <path-to-file>. Focus on missing values, invalid values, dimensions, metadata consistency, and quality concerns.

Compare related files

Analyze these related files and summarize their differences, shared structure, and recommended integration steps: <file-list>.

Plan downstream analysis

Perform format-aware EDA on <path-to-file>, then recommend preprocessing, visualization, statistical analysis, and validation steps for the dataset.

Best Practices

Provide the exact local file path and any known instrument or experiment context.
Install the relevant scientific Python libraries before analyzing specialized formats.
Review generated reports before sharing because they may include filenames and local path details.

Avoid

Do not use it as the only validation step for regulated or clinical datasets.
Do not load very large files fully when sampling or chunked processing is safer.
Do not assume unknown vendor formats are supported without checking the reference guidance.

Frequently Asked Questions

What types of files can this skill analyze?

It covers chemistry, genomics, microscopy, spectroscopy, proteomics, metabolomics, and common scientific formats such as CSV, JSON, HDF5, TIFF, and NumPy arrays.

Does it modify my data files?

No. The analyzer reads input data and writes a separate markdown report.

Can it handle large datasets?

Yes, but large files may need sampling, chunked processing, or memory-mapped access to avoid high memory use.

What happens if a required library is missing?

The report includes a clear error message and suggests the library needed for that format.

Can I use it with Claude Code?

Yes. The skill is designed for Claude Code and also declares support for Claude and Codex workflows.

Does the report include recommendations?

Yes. Reports include next steps for preprocessing, visualization, analysis methods, and format-specific quality checks.