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

60%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/general/exploratory-data-analysis/SKILL.md

Quality

Content

35%

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

The body is well-structured with a clear workflow and useful code examples, but it is verbose (explaining domain concepts Claude already knows and restating the workflow), references a missing analyzer script, and points to bundle files that are absent from the package.

Suggestions

Trim domain background and repeated extension/library lists that Claude already knows; keep only the format-to-reference-file mapping and the per-format analysis steps.

Add an explicit validation/verification checkpoint (e.g., confirm detected format against the reference, retry on parse errors) to the main workflow for batch file analysis.

Either ship the referenced bundle files (references/*.md, scripts/eda_analyzer.py, assets/report_template.md) or remove the references to them so signaled navigation resolves to real content.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded with concepts Claude already knows (enumerated file extensions per domain, what each domain contains, repeated library-install patterns) and restates the workflow as comment pseudocode in the Examples section, plus a self-promotional K-Dense Web plug; it earns the verbose anchor rather than the mostly-efficient level-2 anchor.	1 / 3
Actionability	Provides a concrete script invocation and real code snippets (SeqIO, pandas read_csv, ND2Reader), but the referenced analyzer script does not exist on disk and several examples are comment-style rather than fully executable, leaving guidance incomplete.	2 / 3
Workflow Clarity	A clear five-step sequence is present (detect, load reference, analyze, report, save), but the batch/analysis workflow has no explicit validation checkpoints or fix-and-retry feedback loop, which caps it at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	The markdown is well organized with one-level-deep reference signals per category, but the referenced bundle files (references/*.md, scripts/eda_analyzer.py, assets/report_template.md) do not exist on disk, so the signaled navigation cannot actually be followed.	2 / 3
	Total	7 / 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.

The description is specific, complete, and well-differentiated, with concrete actions and an explicit 'when to use' trigger. Its only weakness is trigger-term breadth: it lacks the concrete natural-language variations and file extensions that would maximize matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations', matching the comprehensive-actions anchor rather than the partial level-2 anchor.	3 / 3
Completeness	Clearly states both what it does (EDA, detection, report generation) and when to use it via the explicit 'This skill should be used when analyzing any scientific data file...' clause, satisfying both halves rather than leaving 'when' only implied.	3 / 3
Trigger Term Quality	Includes natural phrases like 'analyzing any scientific data file' and 'understand its structure, content, quality, and characteristics', but lacks common concrete trigger variations users would say (e.g., file extensions, 'explore'/'summarize'), so it stops short of full coverage.	2 / 3
Distinctiveness Conflict Risk	Scoped to 'scientific data files' with an enumerated domain list (chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics), giving it a clear niche with distinct triggers unlikely to conflict with general-purpose file skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/general/exploratory-data-analysis/SKILL.md
Commit: df37802

Reviewed: about 2 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.