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.

76

Quality

93%

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

87%

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

The body is concise, highly actionable with executable code, and well-organized into a clear five-step workflow with an honest-reporting closing section. The main gap is that validation/feedback checkpoints in the download-and-analyze step are implied rather than explicit.

Suggestions

Add an explicit checkpoint after downloading/loading data (e.g., 'print(df.shape, df.dtypes); assert not df.empty') before proceeding to merge or regression, mirroring the validate-then-proceed pattern.

In Step 4, insert a short feedback loop: if the loader errors or returns an empty frame, inspect the raw bytes/URL and retry with a different format before continuing.

Surface the 'download a small sample first and inspect' guidance as a numbered validation step rather than a parenthetical, so the verify-before-analyze pattern is unmistakable.

DimensionReasoningScore

Conciseness

Lean and action-oriented with no padding explaining what datasets or libraries are; assumes Claude's competence and every section earns its place (e.g., the design-decision table, the data-loading cookbook).

3 / 3

Actionability

Provides fully executable, copy-paste-ready Python (pandas loaders across formats, URL download with format detection, REST API pagination, merge/clean/regression/visualization) plus specific named repositories and concrete commands.

3 / 3

Workflow Clarity

The five-step sequence is clearly ordered, but explicit validation checkpoints are implicit rather than enforced — e.g., no 'verify the download/load succeeded and df is non-empty before regressing' loop, so checkpoints are present but not crisp.

2 / 3

Progressive Disclosure

Single self-contained SKILL.md with no bundle files and no need for external references; content is well-organized into clearly labeled sections (When to Use, Steps 1–5, Cookbook, LOOK UP DON'T GUESS), matching the simple-skill allowance for a 3.

3 / 3

Total

11

/

12

Passed

Description

100%

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 specific, third-person, and clearly answers both what the skill does and when to use it, with natural trigger phrases and a distinct repository-backed niche. It is concise without padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Find and evaluate research datasets' and 'Maps research questions to required study designs (longitudinal vs cross-sectional, observational vs experimental, single-cohort vs multi-cohort)' — matching the anchor that lists several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Find and evaluate research datasets... Maps research questions to required study designs') and when ('Use when the user asks...'), matching the anchor with explicit triggers for both.

3 / 3

Trigger Term Quality

Includes natural phrases users actually say — 'find data about X', 'where can I get data on Y', 'cohort/survey/repository' — giving good coverage of natural terms rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

Clear niche of scientific dataset discovery anchored by named repositories (GEO, ArrayExpress, dbGaP, NHANES, UK Biobank, ClinicalTrials.gov), unlikely to trigger for the wrong skill; uses third-person voice throughout.

3 / 3

Total

12

/

12

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.