CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-statistical-modeling

Perform statistical modeling and regression analysis on biomedical datasets. Supports linear regression, logistic regression (binary/ordinal/multinomial), mixed-effects models, Cox proportional hazards survival analysis, Kaplan-Meier estimation, and comprehensive model diagnostics. Extracts odds ratios, hazard ratios, confidence intervals, p-values, and effect sizes. Designed to solve BixBench statistical reasoning questions involving clinical/experimental data. Use when asked to fit regression models, compute odds ratios, perform survival analysis, run statistical tests, or interpret model coefficients from provided data.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The content is highly actionable with complete, executable code and a sensible phased workflow, but it is verbose and overfit to a specific benchmark. The biggest structural flaw is that every referenced bundle file (references/, scripts/, QUICK_START.md, etc.) is missing, breaking progressive disclosure.

Suggestions

Add the missing bundle files (references/, scripts/, QUICK_START.md, EXAMPLES.md, TOOLS_REFERENCE.md) or remove the dangling references so navigation actually resolves.

Trim general-knowledge explanation (e.g., the statsmodels-vs-scikit-learn rationale and model-selection basics) and relocate exhaustive code examples to the reference files so SKILL.md stays a lean overview.

Replace benchmark-specific 'CRITICAL' callouts (bix-51-q3, bix-36-q1) with generalizable validation rules and add explicit validate→fix→retry feedback loops for batch analyses.

DimensionReasoningScore

Conciseness

The ~550-line body restates concepts Claude already knows (general library comparison rationales, model-selection basics) and embeds dated benchmark specifics ('bix-51-q3', 'bix-36-q1', expected 'F ∈ [0.76, 0.78]'), so it is mostly efficient but could be tightened and trimmed.

2 / 3

Actionability

Provides fully executable statsmodels/lifelines/scipy code blocks with exact formulas for odds ratios, hazard ratios, percentage reduction, and per-feature ANOVA — copy-paste ready and complete.

3 / 3

Workflow Clarity

Phases 0–3 are sequenced with a data-validation checklist and decision trees, but verification is advisory rather than enforced validate→fix→retry feedback loops, and the 'CRITICAL' callouts are benchmark-specific rather than general checkpoints.

2 / 3

Progressive Disclosure

The body repeatedly signals external files ('See references/...', 'QUICK_START.md', 'EXAMPLES.md', 'TOOLS_REFERENCE.md', 'scripts/'), but none of those bundle files actually exist in the skill directory, so the navigation is broken and inline content that should be split out is not.

2 / 3

Total

9

/

12

Passed

Description

100%

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 clearly states capabilities and provides explicit 'Use when' triggers with natural user-facing terminology. Minor overfitting to the BixBench benchmark name slightly narrows the intended audience but does not hurt distinctiveness.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and model families — 'linear regression, logistic regression (binary/ordinal/multinomial), mixed-effects models, Cox proportional hazards survival analysis, Kaplan-Meier estimation' — and concrete outputs like odds ratios, hazard ratios, CIs, p-values, matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

Clearly answers both what (the listed modeling and extraction capabilities) and when via an explicit 'Use when asked to...' clause, matching the anchor for clearly answering both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

Explicit trigger phrasing mirrors what a user would say — 'fit regression models, compute odds ratios, perform survival analysis, run statistical tests, or interpret model coefficients' — giving good coverage of natural terms rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The biomedical statistical-modeling niche and BixBench-oriented framing give a clear, narrow domain with distinct triggers that are unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (558 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 8 missing

Warning

Total

14

/

16

Passed

Repository
wu-yc/LabClaw
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.