tooluniverse-diagnostic-test-evaluation

Diagnostic test / biomarker accuracy — sensitivity, specificity, PPV, NPV, likelihood ratios, accuracy from a 2x2 table; ROC curve, AUC, and the optimal cutoff (Youden) for a continuous biomarker; and post-test probability via Bayes. Use when you have test results vs a gold standard (binary 2x2, or a continuous score + true labels) and need to judge how good the test is, pick a threshold, or compute the probability of disease given a result. Emphasizes the prevalence-dependence of PPV/NPV.

Quality

95%

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

Quality

Content

100%

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

An exemplary skill body: concise, fully actionable, with a clear routing workflow and appropriately split-out detail in a real bundle script.

Dimension	Reasoning	Score
Conciseness	Lean and action-dense with no prose padding: commands, compact reference tables, and targeted gotchas; assumes Claude's competence without explaining what a ROC curve or AUC is in narrative form.	3 / 3
Actionability	Fully executable, copy-paste-ready invocations throughout — `tu run Epidemiology_diagnostic '{...}'`, `ROC_analysis(scores=[...], labels=[...])`, `python skills/.../scripts/roc_analysis.py --input scores.csv`, and `tu run Epidemiology_bayesian '{...}'`.	3 / 3
Workflow Clarity	A "Which case are you in?" routing table funnels into sequenced Steps 1–3 with explicit cross-links ("Once you choose a cutoff, build its 2×2 and run Step 1") and a held-out-validation gotcha; not a batch/destructive task so no validate-fix-retry loop is required.	3 / 3
Progressive Disclosure	Well-organized overview with a one-level-deep, clearly-signaled bundle reference (scripts/roc_analysis.py, verified present on disk) and a Related-skills section; no nested reference chains.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 specific, well-triggered description that names concrete actions and explicit use-conditions; the only weakness is second-person voice ("you have"), which the rubric penalizes on specificity.

Suggestions

Rewrite the trigger clause in third person to avoid the voice penalty, e.g. "Use when test results vs a gold standard are available and one needs to judge test quality, pick a threshold, or compute the probability of disease given a result."

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("sensitivity, specificity, PPV, NPV, likelihood ratios, accuracy from a 2x2 table; ROC curve, AUC, and the optimal cutoff (Youden)... post-test probability via Bayes"), which is anchor-3 content, but the second-person voice ("Use when you have test results") triggers the rubric's -1 specificity penalty.	2 / 3
Completeness	Clearly answers both what (the metric families computed) and when ("Use when you have test results vs a gold standard ... and need to judge how good the test is, pick a threshold, or compute the probability of disease given a result"), with explicit triggers.	3 / 3
Trigger Term Quality	Good coverage of natural terms a user would say — "diagnostic test", "biomarker", "sensitivity/specificity/PPV/NPV", "ROC", "AUC", "gold standard", "probability of disease" — matching the anchor-3 example.	3 / 3
Distinctiveness Conflict Risk	A clear niche (diagnostic-test / biomarker accuracy evaluation) with distinct triggers and prevalence-dependence framing, unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: plugin/skills/tooluniverse-diagnostic-test-evaluation/SKILL.md
Commit: 089eb8e

Reviewed: about 6 hours 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.