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 generate...

Quality

64%

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 ./scientific-skills/Data Analysis/exploratory-data-analysis/SKILL.md

Quality

Content

53%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.

A thorough, well-structured skill with executable code, a working analyzer script, and properly signaled one-level reference files, but it is noticeably verbose due to redundant reference/script listings and verbose examples, and its numbered workflow lacks explicit validation checkpoints. Weakest on conciseness and workflow clarity.

Suggestions

De-duplicate the reference file listings (currently repeated in "Supported File Categories", "Detailed Format References", and "Resources") and merge the "Script Usage" section into Step 3 to remove padding.

Add explicit validation checkpoints to the numbered workflow, e.g. after file-type detection ("Confirm the detected category/format matches the file contents") and before saving the report ("Verify all required report sections are populated").

Trim the three verbose example blocks to concise, copy-paste-ready snippets and move the per-data-type analysis bullet lists into the corresponding reference files.

Dimension	Reasoning	Score
Conciseness	The ~450-line body has noticeable padding: reference files are listed three times (per-category, in "Detailed Format References", and in "Resources"), script usage is explained twice (Step 3 and "Script Usage"), and three verbose example blocks restate the workflow—matching "noticeably verbose; several unnecessary... padded sections" (anchor 2, not the mostly-efficient anchor 3).	2 / 5
Actionability	Provides concrete executable code (pandas, Biopython, nd2reader), a real script invocation ("python scripts/eda_analyzer.py <filepath> [output.md]"), and a regex snippet for searching references, but several examples lean on comment-style pseudo-code ("# Calculate: read count, length distribution, quality scores, GC content") leaving minor gaps (anchor 4, not fully copy-paste anchor 5).	4 / 5
Workflow Clarity	A clear five-step sequence (Detect → Load reference → Analyze → Generate report → Save) is present, but the numbered workflow has no explicit validation checkpoints—format-detection confirmation and report-completeness checks are only implicit—matching "sequence present but checkpoints missing or implicit" (anchor 3, not anchor 4).	3 / 5
Progressive Disclosure	Structure is good: a clear overview signals one-level-deep, real reference files per category (e.g., references/chemistry_molecular_formats.md, verified present), plus a script and template asset, but the body inlines substantial detail (per-type analysis lists, full report section list, three examples) that could live in references and lists references redundantly, so minor organization gaps keep it at anchor 4 rather than 5.	4 / 5
	Total	13 / 20 Passed

Description

75%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.

A solid, mostly specific description that covers both capability and trigger guidance in third person, but it is literally truncated mid-sentence ("generate...") and lacks synonyms and file extensions. It sits at a consistent 4 across dimensions rather than reaching 5.

Suggestions

Complete the truncated sentence ("Automatically detects file type and generate...") so the description is not cut off mid-action.

Add natural synonyms ("explore", "summarize") and representative file extensions (e.g., .csv, .fastq, .nd2, .hdf5) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("scientific data files across 200+ file formats") and several concrete actions—file-type detection, understanding "structure, content, quality, and characteristics"—but the truncated "generate..." leaves the report-generation action incomplete, so coverage is strong but not comprehensive (anchor 4, not 5).	4 / 5
Completeness	It explicitly answers both what ("Perform comprehensive exploratory data analysis... Automatically detects file type") and when ("This skill should be used when analyzing any scientific data file..."), but the dangling truncated sentence "Automatically detects file type and generate..." makes the description literally incomplete, holding it just below the anchor-5 bar.	4 / 5
Trigger Term Quality	Natural terms like "exploratory data analysis", "analyzing any scientific data file", and "scientific data files" would plausibly be said by users, but common synonyms ("explore", "summarize") and file extensions are absent, so a few natural terms are missing (anchor 4, not 5).	4 / 5
Distinctiveness Conflict Risk	"Scientific data files across 200+ file formats" with EDA is a clear, fairly distinct niche with minimal overlap risk for most skills, though "scientific data files" is broad enough to overlap with general data-analysis skills, fitting anchor 4 rather than the fully-distinct anchor 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/exploratory-data-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~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.