CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/exploratory-data-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

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 a properly organized, real bundle, but it is noticeably verbose — teaching concepts Claude already knows — and some example code is illustrative rather than executable. Tightening the tutorial-style sections would lift conciseness; adding a validation checkpoint would round out workflow clarity.

Suggestions

Trim or remove explanations Claude already knows: the grep/regex tutorial in 'Reading Reference Files', the generic pandas/FASTA/image analysis checklists, and the ImportError try/except example — keep only the non-obvious skill-specific guidance.

Make the three 'Examples' copy-paste ready by replacing comment-only pseudo-runs ('# Calculate: ...') with minimal executable code that produces the described outputs.

Add an explicit validation/verification checkpoint in the workflow (e.g., after Step 3, verify expected dimensions/metadata before generating the report) and render reference paths as markdown links for cleaner navigation.

DimensionReasoningScore

Conciseness

Mostly efficient but padded with explanations Claude already knows — a grep tutorial for reading references, a basic pandas 'load/check dimensions/missing values' checklist, and an ImportError try/except example — and several sections (Key Capabilities, Detailed Format References, Examples) overlap heavily.

3 / 5

Actionability

Provides concrete executable code (the analyzer script invocation, pandas/Biopython/nd2reader snippets, a grep lookup pattern), but several example blocks are comment-style pseudo-runs ('# Calculate: read count, length distribution...') rather than copy-paste ready scripts, leaving minor gaps.

4 / 5

Workflow Clarity

A clear five-step sequence (Detect → Load reference → Analyze → Generate report → Save) with per-step sub-instructions and supporting error-handling guidance, but no explicit validate-then-retry feedback loop in the main workflow.

4 / 5

Progressive Disclosure

Well-organized one-level-deep bundle (six real reference files, one script, one asset), each signaled inline by path; minor gaps are that references are named as plain text rather than markdown links and some inlineable example/troubleshooting content could be externalized.

4 / 5

Total

15

/

20

Passed

Description

92%Weight 40%Scale 1-5

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 strong: it explicitly states both what the skill does and when to use it, lists concrete actions, and carves out a distinct niche. The only gap is missing file extensions and common synonym verbs in the trigger language.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Automatically detects file type', 'generates detailed markdown reports', 'format-specific analysis, quality metrics, and downstream analysis recommendations') across a well-defined scientific-data domain — comprehensive coverage matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers 'what' ('Perform comprehensive exploratory data analysis... generates detailed markdown reports...') and 'when' ('This skill should be used when analyzing any scientific data file...') with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Strong domain keywords (chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics) and the natural phrase 'analyzing any scientific data file', but the description omits file extensions and synonym verbs like 'explore'/'summarize' that users also say, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (EDA on scientific data files across named omics/imaging domains) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
foryourhealth111-pixel/Vibe-Skills
Reviewed

Table of Contents

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.