CtrlK
BlogDocsLog inGet started
Tessl Logo

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 content is well-structured, actionable, and concise, with a clearly sequenced workflow containing validation checkpoints and fail-closed boundaries. Progressive disclosure is exemplary: an overview points to one-level-deep reference files that all exist, with explicit guidance not to load them all.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence with no 'what is CSV' filler; the dated pinned-dependency table and citation block add length but are load-bearing rather than padding, leaving only minor trim opportunities.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands across the workflow (capability_manifest.py inspect, eda_analyzer.py, tabular_profile.py, missingness_leakage_audit.py, etc.) with concrete flags and placeholder identifiers, covering the common cases.

5 / 5

Workflow Clarity

A five-step numbered workflow with explicit validation checkpoints ('Manifest before content analysis', 'If status is reference_only, do not run eda_analyzer.py', 'If unknown, stop') supplies clear sequencing and feedback loops for batch/destructive operations.

5 / 5

Progressive Disclosure

SKILL.md is a clear overview with a mapping table to six one-level-deep references (all verified to exist) plus guidance to load only the relevant one, and bundled scripts/assets are appropriately separated with signaled navigation.

5 / 5

Total

19

/

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 comprehensive, concrete, and explicitly pairs a what-clause with a Use-for when-clause, anchored by a clear fail-closed boundary. It is slightly technical in its trigger phrasing rather than mirroring the most common user keywords.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as 'redacted CSV/TSV/JSON profiles', 'missingness/leakage audits', 'outlier and transformation sensitivity', and 'EDA report scaffolds' with named optional formats, giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers what ('Perform bounded, local exploratory analysis...') and when ('Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural trigger terms like 'CSV/TSV/JSON', 'NumPy, HDF5, FASTA/FASTQ', 'missingness/leakage audits', and file extensions, but the phrasing is somewhat technical and a few common user phrasings (e.g., 'exploratory data analysis', 'data profiling') are less prominent, so it sits just below a 5.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche of bounded scientific EDA with an explicit fail-closed boundary ('unknown formats fail closed', 'reference-only'), making it unlikely to trigger for unrelated 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
K-Dense-AI/scientific-agent-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.