tooluniverse-statistical-modeling

Statistical modeling and regression analysis for biomedical data. Linear/logistic/ordinal regression, Cox proportional hazards, mixed-effects models, ANOVA, with odds ratios, hazard ratios, confidence intervals, and model diagnostics.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/tooluniverse-statistical-modeling/SKILL.md

Quality

Content

71%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 highly actionable, well-sequenced skill with strong executable examples and a clear phased workflow. Its main weaknesses are duplicated content inflating length and dangling references to bundle files that are not present.

Suggestions

Remove duplication: keep full logistic/Cox examples in one place (Quick Start or Phase 1, not both) and have Pattern 5 link to the per-feature ANOVA section instead of re-explaining it.

Ship the referenced bundle files (references/*.md, scripts/*.py, QUICK_START.md, TOOLS_REFERENCE.md) or drop the references and File Structure block, so progressive-disclosure navigation is not broken.

Add an explicit feedback loop in Phase 2 (e.g., 'if Shapiro-Wilk or Breusch-Pagan p<0.05, transform or use robust SEs and refit') to complete the validation cycle.

Dimension	Reasoning	Score
Conciseness	The ~571-line body is mostly actionable code rather than concept explanation, but it duplicates content: the Quick Start logistic/Cox examples are re-stated in Phase 1, and Pattern 5 re-covers the already-large per-feature ANOVA block, so it could be meaningfully tightened.	3 / 5
Actionability	Provides copy-paste-ready, executable code (statsmodels, lifelines, scipy) across logistic, ordinal, Cox, ANOVA, diagnostics, and interpretation, covering the common cases with specific outputs.	5 / 5
Workflow Clarity	Phases 0–3 are clearly sequenced with a Phase 0 data-validation gate, a completeness checklist, and ❌/✅ error-recovery examples, though the diagnostics phase lacks an explicit 'assumption violated → refit' feedback loop.	4 / 5
Progressive Disclosure	Section structure is clear and references are signaled one level deep, but the referenced bundle files (QUICK_START.md, references/.md, scripts/.py, TOOLS_REFERENCE.md) do not exist, so navigation is broken, and heavy detail is inlined rather than offloaded.	3 / 5
	Total	15 / 20 Passed

Description

71%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 specific, capability-rich description that clearly conveys what the skill does, but it omits an explicit 'when to use' trigger clause, capping its completeness. Trigger-term coverage is good but lacks a few natural synonyms.

Suggestions

Append a 'Use when...' clause naming concrete triggers (e.g., 'Use when users ask for odds ratios, hazard ratios, Kaplan-Meier estimates, or regression on biomedical data') to lift completeness.

Add natural synonyms users say — 'survival analysis', 'p-values', 'confidence intervals' are present but 'Kaplan-Meier' and 'inference' would broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across model families — 'Linear/logistic/ordinal regression, Cox proportional hazards, mixed-effects models, ANOVA, with odds ratios, hazard ratios, confidence intervals, and model diagnostics' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural terms a biomedical analyst would say ('odds ratios', 'hazard ratios', 'ANOVA', 'regression'), but misses common synonyms such as 'survival analysis' and 'p-values' that users frequently request.	4 / 5
Distinctiveness Conflict Risk	The biomedical inferential niche (Cox PH, mixed-effects, odds/hazard ratios) is mostly distinct from general stats or ML skills, with only minor overlap risk with broader regression tools.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (578 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	13 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/tooluniverse-statistical-modeling/SKILL.md
Commit: f5ef65b

Reviewed: ~10 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.