Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Dataset Discovery · mims-harvard | DecimalAI

researchby mims-harvard

Dataset Discovery

mims-harvard/tooluniverse-dataset-discovery

Source mims-harvard/ToolUniverse ↗License Apache-2.0

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).

SkillScore64Maintained

Automatic

Research pack

Last verified 8/6/2026

What it changes

Passed 11 of 17 test cases with the skill, and 10 of 17 without it.

Without skill59%

With skill64%

Checks it passed that the model alone missed

Includes a dedicated recommendations section outlining future dataset acquisition steps.
States explicitly that cross-sectional survey data cannot evaluate temporal disease incidence.
States that longitudinal data tracking the same individuals across multiple waves is required to assess temporal change.

2 fixed12 passed either way7 still failing1 broke

Pass-rate lift: +5 pp
Tokens: +90%
Agent turns: 0%
Response time: +9%

Model gemini-3.6-flashMeasured 8/6/2026v1 · latest is v214 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/mims-harvard-tooluniverse-dataset-discovery/SKILL.md https://app.decimal.ai/s/mims-harvard-tooluniverse-dataset-discovery/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add mims-harvard-tooluniverse-dataset-discovery, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/mims-harvard-tooluniverse-dataset-discovery/ and pins it in .decimal/skills.lock

decimalai skills add mims-harvard-tooluniverse-dataset-discovery

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/mims-harvard-tooluniverse-dataset-discovery/SKILL.md https://app.decimal.ai/s/mims-harvard-tooluniverse-dataset-discovery/SKILL.md

Raw file: /s/mims-harvard-tooluniverse-dataset-discovery/SKILL.md ↗ · machine-readable summary at /s/mims-harvard-tooluniverse-dataset-discovery.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

I want to test if increasing physical exercise causes a reduction in 5-year incidence of cardiovascular events in middle-aged adults. I found a single cross-sectional survey with 50,000 participants that recorded exercise frequency and past heart attack history. Should I run a logistic regression on this dataset and claim exercise reduces 5-year event risk?

What was checked, without and with the skill
Checked	Without skill	With skill
Rejects claiming causal or temporal 5-year risk reduction based on single cross-sectional survey data.	Passed	Passed
States that longitudinal data tracking the same individuals across multiple waves is required to assess temporal change.	Missed	Passed

case-04 · gemini-3.6-flash · 8/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md178 linessingle file

Dataset Discovery

When to Use

User asks "find me data about X" or "where can I get data on Y"
User wants to analyze a relationship between variables
User needs specific study designs (longitudinal, cross-sectional, experimental)
User asks about specific surveys or cohorts

Step 1: Understand What the Research Question Requires

Before searching, determine the minimum data requirements:

Study design needed:

"Does X predict CHANGES in Y over time?" → longitudinal (same people measured repeatedly). Cross-sectional data CANNOT answer this — don't settle for it.
"Is X associated with Y?" → cross-sectional is sufficient (one-time measurement)
"Does intervention X cause outcome Y?" → experimental (clinical trial with controls)
"What genes/proteins are involved in X?" → omics (sequencing, expression, proteomics)

Variables needed:

List the specific exposure, outcome, and confounder variables
For each variable, note the measurement type (continuous, categorical, biomarker vs self-report)
Identify minimum confounders needed (age, sex are almost always required; domain-specific confounders depend on the question)

Population needed:

Age range, geography, clinical status, sample size requirements
Power analysis: to detect a small effect (r=0.1), you need ~800 subjects at 80% power

Step 2: Search Strategy

Search from broadest to most specific. Use find_tools to discover available dataset search tools — don't rely on memorized tool names.

Layer 1 — Cross-repository search (cast wide net): Search tools that index datasets across thousands of repositories. These find datasets you didn't know existed.

Search by: research topic keywords, variable names, population descriptors
Look for: DOI-registered datasets, repository listings, government data portals

Layer 2 — Domain-specific repositories: Search repositories specialized for your data type.

Health surveys: CDC, NHANES (US; search by variable name, not topic keywords); DHS Program (DHSProgram_search_indicators/_get_data) for the international/LMIC equivalent -- fertility, maternal/child mortality, nutrition, immunization, HIV indicators across national surveys, filterable by country and year
Genomics (open): SRA, ENA, ArrayExpress, GEO, and DDBJ (DDBJ_search_entries/_get_entry/_get_cross_references) -- the third INSDC archive alongside SRA/ENA, plus GEA/MetaboBank entries; also GSA (GSA_get_accession) for China's national genomics archive

Track record

Benchmark

11 / 17

test cases passed, vs 10 / 17 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/22/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mims-harvard / ToolUniverse

plugins/tooluniverse/skills/tooluniverse-dataset-discovery/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 9/22/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Dataset Discovery

When to Use

Step 1: Understand What the Research Question Requires

Step 2: Search Strategy

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills