CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-dataset-discovery

Find and evaluate research datasets for any scientific question. Maps research questions to required study designs (longitudinal vs cross-sectional, observational vs experimental, single-cohort vs multi-cohort). Use when the user asks 'find data about X', 'where can I get data on Y', or needs a specific cohort/survey/repository. Covers GEO, ArrayExpress, dbGaP, NHANES, UK Biobank, ClinicalTrials.gov, GWAS Catalog, and 30+ scientific repositories.

74

Quality

91%

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

82%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 highly actionable with executable code and a clear sequenced workflow, supported by concrete fitness and honesty checklists. It is efficient though slightly above lean, and the inline code cookbook could arguably be moved to a reference file.

Suggestions

Trim behavioral-coaching lines (e.g. "Don't stop at finding datasets — download and analyze them", "Never describe what you 'would do' — execute it") to tighten conciseness toward the lean anchor.

Add an explicit validate-and-retry feedback loop (e.g. if no candidate dataset passes the Step-3 fitness check, return to Step 2 with refined search terms) to strengthen workflow_clarity.

Consider moving the ~40-line data-loading cookbook into a references/ file referenced from Step 4 to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and mostly operational, but a few behavioral-coaching lines ("Don't stop at finding datasets — download and analyze them", "Never describe what you 'would do' — execute it") and motivational emphasis could be trimmed; efficient but slightly above lean.

4 / 5

Actionability

Provides fully executable, copy-paste-ready Python covering tabular loaders, URL downloads, REST API pagination, merge/clean, regression, and visualization, plus a concrete per-dataset fitness checklist and the find_tools instruction.

5 / 5

Workflow Clarity

A clearly sequenced five-step process with a Step-3 fitness checklist and honesty/validation rules in Step 5, but explicit validate-and-retry feedback loops for search/fitness failures are mostly implicit rather than spelled out.

4 / 5

Progressive Disclosure

Well-organized into clear sections (When to Use, Steps 1–5, cookbook), and with no bundle files present everything lives inline; the long data-loading cookbook could be split into a reference file, leaving a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, maps research questions to study designs, and gives explicit, natural trigger phrases with named repositories. It fully answers both 'what' and 'when' with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Find and evaluate research datasets", "Maps research questions to required study designs (longitudinal vs cross-sectional, observational vs experimental, single-cohort vs multi-cohort)" — with comprehensive coverage, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both what ("Find and evaluate research datasets... Maps research questions to required study designs") and when ("Use when the user asks 'find data about X'...") with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural user phrasings ("find data about X", "where can I get data on Y") plus concrete repository names (GEO, ArrayExpress, dbGaP, NHANES, UK Biobank), giving comprehensive natural-term coverage with synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (scientific dataset discovery) with distinct triggers tied to specific study designs and named repositories, yielding minimal conflict risk with other skills.

5 / 5

Total

20

/

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
mims-harvard/ToolUniverse
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.