CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-epidemiological-analysis

End-to-end observational epidemiology analysis — from research question (PECO Population/Exposure/Comparator/Outcome) to publication-ready statistical report. Covers cohort/case-control/cross-sectional design, regression with confounders, propensity scoring, sensitivity analysis. Writes Python code for every step. Use for epidemiology study analysis, NHANES/UK-Biobank-style analyses.

72

Quality

87%

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.

A thorough, executable epidemiology workflow with strong code examples and a useful completeness checklist. The main improvement areas are making error-recovery feedback loops explicit and splitting some catalog/template material into reference files.

Suggestions

Add explicit validate→fix→retry loops for fragile steps (e.g., model convergence failures in regression, empty API pagination) so error recovery is spelled out rather than implied.

Extract the Step 7 ToolUniverse tool catalog and the Step 9 report template into a separate references file (e.g., references/report-template.md) to slim SKILL.md and improve progressive disclosure.

Trim editorial asides and consolidate the repeated find_tools("...") placeholder calls into a single parametrized example to improve conciseness.

DimensionReasoningScore

Conciseness

Largely efficient and code-first with little conceptual padding, but a few editorial asides ('This is where ToolUniverse adds value beyond any statistics package') and repeated placeholder find_tools calls could be trimmed.

4 / 5

Actionability

Fully executable, copy-paste-ready Python across every step with concrete function definitions and variable names; placeholders (url1, threshold) are explicitly justified as adapt-to-your-data flexibility.

5 / 5

Workflow Clarity

A clear 9-step sequence with a completeness checklist and validation touches (power analysis, VIF, pagination guard, missing-data decision rules), though explicit validate→fix→retry feedback loops are mostly implicit rather than spelled out.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear section headers and no nested or broken references, but at ~262 lines material such as the ToolUniverse biological-interpretation tool catalog and report template could be split into reference files.

4 / 5

Total

17

/

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.

A strong, specific description that names concrete capabilities and provides explicit trigger guidance with recognizable real-world analysis scenarios. Slightly narrow trigger-term coverage is the only minor weakness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — PECO formulation, regression with confounders, propensity scoring, sensitivity analysis, publication-ready report — with comprehensive coverage of the epidemiology workflow.

5 / 5

Completeness

Explicitly answers both 'what' (end-to-end observational epidemiology analysis to publication-ready report) and 'when' via the concrete 'Use for epidemiology study analysis, NHANES/UK-Biobank-style analyses' trigger clause.

5 / 5

Trigger Term Quality

Includes natural terms like 'epidemiology study analysis' and 'NHANES/UK-Biobank-style analyses', but misses common synonyms a user might say such as 'cohort study' or 'observational study design'.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (observational epidemiology with PECO/cohort/case-control design) with distinct triggers and minimal overlap risk against general data-analysis 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
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.