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

78%

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 ./backend/cli/skills/coding/exploratory-data-analysis/SKILL.md

The canonical home for this skill is exploratory-data-analysis in K-Dense-AI/scientific-agent-skills

Quality

Content

72%

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

A well-structured, actionable skill body with strong progressive disclosure and executable examples. The main gaps are token-efficiency (redundant sections and inline extension lists) and the absence of an explicit validation checkpoint in the workflow.

Suggestions

Remove or compress the 'Key Capabilities', 'When to Use', and 'Resources' sections that restate the description, and replace the inline per-category extension lists with a pointer to the corresponding reference file to reduce duplication.

Insert an explicit verification step in the workflow — e.g. after file-type detection confirm the format against the reference, and after report generation verify required report sections are populated — to add a validation checkpoint.

Replace illustrative comment placeholders like '# Calculate: read count, length distribution...' with concrete executable lines so every example is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The ~435-line body is mostly useful but padded — 'Key Capabilities', 'When to Use', and 'Resources' sections overlap the description, and inline per-category extension lists duplicate content already in the reference files — so it could be tightened without losing clarity.	2 / 3
Actionability	Provides fully runnable guidance — `python scripts/eda_analyzer.py data.csv`, real imports (SeqIO, pandas, ND2Reader), and a copy-paste report template — matching the anchor for executable, specific, copy-paste-ready examples.	3 / 3
Workflow Clarity	The 5-step workflow (detect → load info → analyze → report → save) is clearly sequenced, but there is no explicit validation or verification checkpoint inside the flow, leaving checkpoints implicit rather than enforced.	2 / 3
Progressive Disclosure	SKILL.md is an overview pointing one level deep to six verified reference files, one script, and one asset template, all clearly signaled by path and organized by category — content is appropriately split and easy to navigate.	3 / 3
	Total	10 / 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 concrete capabilities and an explicit use-trigger, with good domain-level distinctiveness. Its main weakness is trigger-term breadth, omitting common verbs and specific extensions users are likely to mention.

Suggestions

Add common natural trigger verbs such as 'explore' and 'summarize' alongside 'analyze', and include a few concrete extensions (e.g. .csv, .fastq, .pdb) so the description matches how users actually phrase requests.

Tighten the closing domain list into a more scannable trigger phrase to avoid mild verbosity without losing the distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Automatically detects file type', 'generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (detects file type, generates reports with quality metrics) and when via the 'This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics' trigger clause.	3 / 3
Trigger Term Quality	Includes relevant keywords ('analyzing any scientific data file') and seven named domains, but misses common natural variations users would say such as 'explore', 'summarize', or specific extensions like .csv/.fastq, so it is not full coverage.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche — EDA of scientific data files across 200+ formats in named scientific domains — with distinct triggers unlikely to fire for generic document or code skills; third-person voice, no penalty applied.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/exploratory-data-analysis/SKILL.md
Commit: 52845c3

Reviewed: about 13 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.