CtrlK
BlogDocsLog inGet started
Tessl Logo

roc-diagnostic-performance

Use when evaluating diagnostic biomarker performance from case-control expression data with logistic regression and ROC curves, exporting coefficient and AUC tables together with a ROC PDF. NOT for: survival analysis, time-to-event outcomes, multiclass classification, calibration curves, decision-curve analysis, or nomogram construction.

74

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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.

The body is highly actionable and well-organized with clear progressive disclosure to real reference files. The main gaps are a few non-existent test-path references and the absence of explicit mid-workflow validation feedback loops for a batch/write operation.

Suggestions

Add explicit validation checkpoints to the Workflow section (e.g., 'After Step 1, confirm matched sample counts meet minimums; if not, stop and report') to create a validate→fix→retry loop for the batch write operation.

Remove or fix dangling references: tests/data/, tests/run_smoke_test.R, and tests/run_smoke_test.sh are cited in the body but are not present in the bundle.

Trim the 'Implementation Checklist' and the repeated full-CLI 'Examples' block to reduce redundancy with the Usage and Arguments sections.

DimensionReasoningScore

Conciseness

Largely efficient reference content (argument, I/O, and error tables) with no conceptual padding, but the 'Implementation Checklist' duplicates other sections and the Examples repeat the full CLI block already shown in Usage.

4 / 5

Actionability

Fully executable, copy-paste-ready Rscript commands with concrete argument tables, input-format examples, and multiple worked examples covering basic, customized, and test-data cases.

5 / 5

Workflow Clarity

A clear five-step pipeline (Validate → Prepare → Fit → Compute → Save) plus an Error Handling table and a Testing/smoke-test section provide verification, but the inline Workflow steps lack explicit validate→fix→retry feedback checkpoints for this batch/--overwrite operation.

4 / 5

Progressive Disclosure

Well-structured overview with a 'When to Read External Files' table mapping situations to one-level-deep references signaled via 'READ:' directives, but several referenced paths (tests/data/, tests/run_smoke_test.R, tests/run_smoke_test.sh) do not exist in the bundle.

4 / 5

Total

17

/

20

Passed

Description

100%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.

The description is excellent: it states concrete capabilities, opens with a natural 'Use when' trigger, and disambiguates with a specific 'NOT for' boundary. It uses third-person/trigger voice and avoids vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'evaluating diagnostic biomarker performance', 'logistic regression', 'ROC curves', 'exporting coefficient and AUC tables together with a ROC PDF' — giving comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers both what (evaluate biomarker performance via logistic regression/ROC, export tables and PDF) and when ('Use when evaluating...') with concrete trigger phrases and a 'NOT for' boundary.

5 / 5

Trigger Term Quality

Covers natural domain terms a user would say ('diagnostic biomarker performance', 'case-control', 'ROC curves', 'AUC', 'logistic regression') plus synonym-style anti-triggers ('survival analysis', 'calibration curves', 'nomogram').

5 / 5

Distinctiveness Conflict Risk

A clear niche (diagnostic ROC from case-control expression data) with an explicit exclusion list ruling out survival, multiclass, calibration, DCA, and nomogram skills, minimizing conflict risk.

5 / 5

Total

20

/

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
aipoch/medical-research-skills
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.