tooluniverse-statistical-modeling

Statistical modeling — linear/logistic/ordinal/Poisson regression, ANOVA, Kruskal-Wallis, chi-square, Mann-Whitney, Cox survival, spline fits (R `ns()`), odds ratios, Cohen's d, F-statistic, p-value computation. Specializes in clinical-trial AE analysis (SDTM DM/AE), severity ordinal regression, and per-feature stat workflows.

Quality

73%

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 ./plugins/tooluniverse/skills/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.

The body is highly actionable with concrete scripts, clear gotchas, and a well-sequenced workflow, but it suffers from significant duplicated sections and several broken references to bundle files that are not present.

Suggestions

De-duplicate the AE-severity, per-gene ANOVA, and R-vs-Python spline sections — keep one canonical location and cross-reference it instead of repeating verbatim.

Fix or remove dead references: anova_and_tests.md and common_patterns_summary.md are cited repeatedly but absent from references/, and QUICK_START.md/EXAMPLES.md/TOOLS_REFERENCE.md/test_skill.py in the File Structure block do not exist.

Move the detailed reasoning-framework and evidence-grading material into a reference file to reduce the inlined body length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the AE-severity 'no AEPT filter' guidance, the per-gene ANOVA aggregation rules, and the R-vs-Python spline warning each appear nearly verbatim twice (once in 'CRITICAL' and again in 'Analysis conventions'), which is unnecessary duplication.	3 / 5
Actionability	Fully executable, copy-paste-ready bash commands with concrete flags, wrong/right code examples, and Python snippets that cover the common recurring question patterns.	5 / 5
Workflow Clarity	A clear RULE ZERO -> PRIMARY SCRIPTS -> Phase 0-3 sequence with a completeness checklist and a workspace-isolation guard (scripts refuse to write into the input dir), though explicit validate->fix->retry feedback loops are not strongly emphasized.	4 / 5
Progressive Disclosure	References are mostly one-level-deep and clearly signaled, but several referenced files do not exist in the bundle (anova_and_tests.md, common_patterns_summary.md, QUICK_START.md, EXAMPLES.md, TOOLS_REFERENCE.md), and the 660-line body inlines substantial material that could live in the reference files.	3 / 5
	Total	15 / 20 Passed

Description

75%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 specific and distinct, listing many concrete statistical capabilities and a clear clinical-trial niche, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness score.

Suggestions

Add an explicit 'Use when...' clause listing the natural trigger phrases (e.g., odds ratio, hazard ratio, survival analysis, ordinal regression, ANOVA F-statistic).

Include commonly-searched synonyms like 'survival analysis', 'hazard ratio', and 'confidence interval' alongside the existing trigger terms.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions/models (linear/logistic/ordinal/Poisson regression, ANOVA, Kruskal-Wallis, chi-square, Mann-Whitney, Cox, spline fits, odds ratios, Cohen's d, F-statistic, p-value), giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Clearly states 'what' the skill does, but there is no explicit 'Use when...' clause or equivalent trigger guidance; the 'when' is only weakly implied via 'Specializes in...', which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Strong coverage of natural statistical trigger terms ('odds ratio', 'ANOVA', 'chi-square', 'F-statistic', 'p-value', 'Cox survival'), but a few common phrases users say ('survival analysis', 'hazard ratio', 'confidence interval') are missing or only implied.	4 / 5
Distinctiveness Conflict Risk	The specialization clause ('clinical-trial AE analysis (SDTM DM/AE), severity ordinal regression, per-feature stat workflows') carves a clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (660 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugins/tooluniverse/skills/tooluniverse-statistical-modeling/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.