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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured skill body with strong progressive disclosure, an executable bundled analyzer, and a clear sequenced workflow. Its chief weakness is conciseness: the body carries redundant sections and restates concepts Claude already knows, inflating the token budget.

Suggestions

Remove redundancy: drop or trim the Examples section (it restates the workflow) and the Resources list (it duplicates Supported File Categories), pointing to the relevant sections instead.

Cut the generic analysis bullet lists (e.g., 'Load with pandas / Check dimensions / Calculate summary statistics') that restate knowledge Claude already has, keeping only format-specific or non-obvious guidance.

Tighten Best Practices > Reading Reference Files by dropping the inline Python regex example in favor of a one-line grep instruction.

Dimension	Reasoning	Score
Conciseness	The ~440-line body is mostly efficient but includes redundancy (Examples restates the workflow, Resources duplicates the reference-file list already given under Supported File Categories, Script Usage restates Step 3) and explains basics Claude already knows (pandas/FASTA analysis steps), fitting 'mostly efficient but could be tightened'.	2 / 3
Actionability	Provides fully executable guidance — `python scripts/eda_analyzer.py <filepath>`, real library calls (SeqIO.parse, pd.read_csv, ND2Reader), a working reference-lookup regex, and install snippets — meeting 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	A clear 5-step sequence (Detect → Load info → Analyze → Generate report → Save) with a required-sections report checklist and troubleshooting/error-recovery guidance; the task is read-only EDA so the destructive-validation cap does not apply.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points to six one-level-deep category reference files (all verified present), plus the analyzer script and report template, each clearly signaled and easy to navigate — textbook 'clear overview with well-signaled one-level-deep references'.	3 / 3
	Total	11 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states capabilities and an explicit use-when trigger with a well-defined scientific-data niche. Its main weakness is trigger-term breadth: it relies on 'analyzing' and omits natural variations like 'explore' and 'summarize' that users commonly say.

Suggestions

Broaden trigger terms to include natural user phrasings such as 'explore', 'summarize', or 'profile a data file', not just 'analyzing'.

Add a few representative file extensions (e.g., .fastq, .pdb, .csv, .nd2) so the description surfaces for format-specific requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Perform comprehensive exploratory data analysis', 'Automatically detects file type and generates detailed markdown reports', and 'format-specific analysis, quality metrics, and downstream analysis recommendations' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what (EDA, detection, report generation) and when ('This skill should be used when analyzing any scientific data file...'), satisfying the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Includes a relevant trigger ('when analyzing any scientific data file to understand its structure, content, quality, and characteristics') but lacks common natural variations users would say ('explore', 'summarize') and specific format extensions, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	A clear niche — scientific data files across 200+ formats spanning named domains (chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics) — makes it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/exploratory-data-analysis/SKILL.md
Commit: f627ab5

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.