Name: tooluniverse-epidemiological-analysis
Rating: 67.2 (1 reviews)
Author: mims-harvard

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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/tooluniverse/skills/tooluniverse-epidemiological-analysis/SKILL.md

The canonical home for this skill is tooluniverse-epidemiological-analysis in mims-harvard/ToolUniverse

Quality

Content

68%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.

Highly actionable with executable code throughout and a clear sequenced workflow plus checklist, but it is a long monolithic document that explains concepts Claude already knows and would benefit from splitting reference material into separate files.

Suggestions

Split the reusable code (power analysis, download helper, regression templates, plotting specs) into reference files under ./references/ and keep SKILL.md as a concise overview with one-level-deep pointers.

Trim concept-level explanation Claude already knows (e.g., the PECO letter definitions and study-design primer) and keep only workflow-specific guidance.

Add explicit validation checkpoints for fragile steps — e.g., verify the download/merge produced expected row counts before analysis, and confirm model convergence before interpreting ORs.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code blocks driving each step, but it pads several sections with concept-level explanation Claude already knows (e.g., defining what PECO letters mean, restating study-design definitions, listing Table 1 conventions), and the body is long (~260 lines) for a workflow overview.	3 / 5
Actionability	Provides fully executable, copy-paste-ready Python for every step — power analysis, download/parse, Table 1, sequential logistic regression, VIF, stratified and outlier sensitivity analyses — covering the common cases with real code rather than pseudocode.	5 / 5
Workflow Clarity	A clear nine-step sequence with a final completeness checklist acting as a validation checkpoint; however, several code-bearing steps (data download, regression fit) lack explicit 'verify before proceeding' validation or error-recovery feedback loops, which is below the score-5 bar.	4 / 5
Progressive Disclosure	No bundle files exist and the SKILL.md is a monolithic 260-line body that inlines substantial reference material (power-analysis formulas, full regression code, visualization specs) that would be better placed in separate reference files, with only a high-level overview in SKILL.md.	2 / 5
	Total	14 / 20 Passed

Description

91%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 covers the full epidemiology workflow and gives an explicit 'Use for ...' trigger clause. Minor improvement would come from adding more natural trigger synonyms users might say.

Suggestions

Add natural trigger synonyms users are likely to say, such as 'observational study', 'cohort analysis', 'risk factor analysis', or 'case-control study'.

Consider naming outcome types in the trigger (e.g., 'disease incidence, survival, biomarker outcomes') to broaden natural-language match.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full workflow — PECO framing, cohort/case-control/cross-sectional design, regression with confounders, propensity scoring, and sensitivity analysis — covering the domain comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (the end-to-end analysis and statistical steps it performs) and 'when' via the closing 'Use for epidemiology study analysis, NHANES/UK-Biobank-style analyses' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases like 'epidemiology study analysis' and the named NHANES/UK-Biobank styles, but lacks several common variations and synonyms a user might naturally say (e.g., 'observational study', 'risk factor analysis', 'cohort analysis').	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (observational epidemiology with PECO and biological-plausibility steps) with distinct triggers unlikely to fire for general statistics or bioinformatics skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-epidemiological-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.