Skills exploratory-data-analysis
📦

exploratory-data-analysis

Content revision r1 Medium Risk 📁 Filesystem access⚙️ External commands

Analyze Scientific Data Files

Scientific data files can be difficult to inspect before analysis. This skill detects formats, summarizes data quality, and creates practical EDA reports.

Supports: Claude Codex Code(CC)
📊 76 Adequate

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/k-dense-ai-exploratory-data-analysis.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-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/k-dense-ai-exploratory-data-analysis.md Signed manifest GET /api/skills/k-dense-ai-exploratory-data-analysis/manifest Signed lockfile GET /api/skills/k-dense-ai-exploratory-data-analysis/lockfile

Test it

Using "exploratory-data-analysis". A researcher asks for EDA on experiment_results.csv.

Expected outcome:

A markdown report lists row and column counts, data types, missing values, summary statistics, outlier concerns, and preprocessing suggestions.

Using "exploratory-data-analysis". A bioinformatics user provides reads.fastq.

Expected outcome:

The response identifies FASTQ format, summarizes sampled read lengths and quality metrics, and recommends sequence QC steps.

Using "exploratory-data-analysis". A microscopy team provides cells.tif.

Expected outcome:

The report describes image dimensions, pixel type, value range, intensity statistics, page count, and suitable segmentation checks.

Security Audit

Medium Risk
v9 • 7/9/2026 Open versioned report

Most static findings are false positives caused by Markdown code formatting, scientific file-format terminology, and documentation examples. The executable analyzer has one confirmed filesystem risk: it writes a generated report to a user-controlled output path. Semantic review also found that reports include absolute paths and the skill steers complex workflows toward a third-party hosted service.

9
Files scanned
4,813
Lines analyzed
1
Review items
0
False positives ignored

Confirmed security concerns (2)

Medium
SKILL.md:445-446
Off-Platform Service Steering for Sensitive Workflows
The skill instructs the assistant to suggest a hosted K-Dense Web service for complex dataset exploration. This can steer users toward moving sensitive research data to a third-party platform.
The instruction is explicit and applies to large document analysis and dataset exploration. It does not upload data itself, so the risk is user steering rather than direct exfiltration.
Low
scripts/eda_analyzer.py:441
Full Local Path Disclosure in Reports
Generated reports include the absolute path of the analyzed file. Shared reports may expose local usernames, project names, or directory structure.
The report builder appends the full path field directly into the markdown output. This is a clear disclosure risk when reports are shared.
Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
scripts/eda_analyzer.py:508
Python file write/append
with open(output_path, 'w') as f:
The analyzer writes a markdown report to output_path with write mode. Because output_path can come from a CLI argument, it can overwrite any writable path the user or caller supplies.

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:377
⚙️ External commands (55)
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:41 SKILL.md:43 SKILL.md:48 SKILL.md:50 SKILL.md:55 SKILL.md:57 SKILL.md:62 SKILL.md:64 SKILL.md:69 SKILL.md:71 SKILL.md:76 SKILL.md:78 SKILL.md:92-98 SKILL.md:98-108 SKILL.md:108-112 SKILL.md:112-115 SKILL.md:115-123 SKILL.md:123-191 SKILL.md:191-196 SKILL.md:196-197 SKILL.md:197 SKILL.md:218-224 SKILL.md:224 SKILL.md:225 SKILL.md:231-240 SKILL.md:240-246 SKILL.md:246-270 SKILL.md:270-289 SKILL.md:289-293 SKILL.md:293-313 SKILL.md:313-317 SKILL.md:317-338 SKILL.md:338-349 SKILL.md:349-354 SKILL.md:354-357 SKILL.md:357 SKILL.md:358 SKILL.md:359 SKILL.md:360 SKILL.md:361 SKILL.md:383-385 SKILL.md:385-397 SKILL.md:397-432 SKILL.md:432-435 SKILL.md:435-436 SKILL.md:436-437 SKILL.md:437-438 SKILL.md:438-439 SKILL.md:439-440 SKILL.md:440-443
Audited by: codex 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
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-exploratory-data-analysis/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-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

K-Dense-AI. (2026). exploratory-data-analysis security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-exploratory-data-analysis/audits/9

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-exploratory-data-analysis-2026, author = {K-Dense-AI}, title = {exploratory-data-analysis security audit report (audit version 9)}, institution = {Skillstore}, year = {2026}, number = {9}, url = {https://skillstore.io/skills/k-dense-ai-exploratory-data-analysis/audits/9}, 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 9)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-09" url: "https://skillstore.io/skills/k-dense-ai-exploratory-data-analysis/audits/9" identifiers: - type: other value: "skillstore:k-dense-ai-exploratory-data-analysis:audit:9" 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
davila7 Recommended

davila7-exploratory-data-analysis

Skillstore Score 85
Evidence Confidence High
Skillstore usage 58
Updated

2026-08-21

K-Dense-AI Current

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
82
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance

What You Can Build

Profile a New Experiment Dataset

Inspect file structure, dimensions, missing values, and basic statistics before modeling or visualization.

Check Sequencing Files Before QC

Summarize sequence counts, length distributions, quality signals, and likely next bioinformatics steps.

Document Data for Handoff

Create a markdown summary that explains file formats, metadata, quality concerns, and recommended analysis paths.

Try These Prompts

Analyze One File 
Analyze this scientific file: [path]. Identify the format, summarize metadata, assess data quality, and create an EDA report.
Compare Related Files 
Compare these related data files: [paths]. Highlight shared structure, differences, missing data, and recommended preprocessing.
Plan Downstream Analysis 
Review [path] for downstream analysis planning. Explain required libraries, sampling limits, quality concerns, and suitable visualization methods.
Build an EDA Workflow 
Build a reproducible EDA workflow for [dataset paths]. Include format-specific checks, cross-file consistency checks, report sections, and sharing risks.

Best Practices

  • Share the file path, expected scientific domain, and any known instrument or processing context.
  • Use sampling for very large files and state the sampling method in the report.
  • Review generated reports for sensitive paths or identifiers before sending them outside your workspace.

Avoid

  • Do not treat sampled EDA as a complete audit of every record.
  • Do not assume specialized formats can be parsed without the required libraries installed.
  • Do not share reports containing absolute paths, sample IDs, or protected research metadata.

Frequently Asked Questions

What file types does this skill support?
It documents many scientific formats and automates analysis for common tables, arrays, JSON, HDF5, sequences, and images.
Does it install scientific Python libraries?
No. It reports missing libraries and suggests packages that may be needed for specialized formats.
Can it analyze very large files?
Yes, but it may sample records or recommend chunked analysis to keep the review practical.
What does the generated report include?
The report covers basic file details, format identification, data summaries, quality notes, key findings, and next analysis ideas.
Is it limited to one scientific domain?
No. It covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data.
Can I use it with Claude, Codex, and Claude Code?
Yes. The marketplace metadata lists support for Claude, Codex, and Claude Code.

Developer Details

Author

K-Dense-AI

License

MIT license

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/exploratory-data-analysis

Ref

26421118b848d9f1efc0aa169d8a7a9e7e0a877e

Maintenance freshness

7/18/2026

Usage

36 downloads · 263 views

File structure

📁 assets/

📄 report_template.md

📁 references/

📄 bioinformatics_genomics_formats.md

📄 chemistry_molecular_formats.md

📄 general_scientific_formats.md

📄 microscopy_imaging_formats.md

📄 proteomics_metabolomics_formats.md

📄 spectroscopy_analytical_formats.md

📁 scripts/

📄 eda_analyzer.py

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all