statsmodels

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Quality

75%

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 ./bundled/skills/statsmodels/SKILL.md

Quality

Content

75%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 delivers highly actionable, executable guidance with well-structured one-level-deep references to real bundle files, but it is somewhat verbose due to a duplicated reference section and restatement of well-known statistical best practices. Tightening the redundant sections would improve token efficiency.

Suggestions

Remove or collapse the 'Reference Documentation' section (lines 514-582) since it duplicates the inline reference callouts and the bundle files' own contents.

Trim 'Best Practices' and 'Common Pitfalls' to only the non-obvious statsmodels-specific gotchas, dropping domain knowledge Claude already knows (e.g. reporting effect sizes, data leakage).

Add explicit validation feedback loops to at least the time-series and count-data workflows (e.g. 'If ADF p-value > 0.05, difference and re-test before fitting').

Dimension	Reasoning	Score
Conciseness	The ~600-line body is mostly efficient with valuable executable code, but the 'Reference Documentation' section restates content already covered in the capability sections, and the 'Best Practices'/'Common Pitfalls' lists restate domain knowledge Claude already knows (e.g. adding a constant, reporting effect sizes), fitting the mostly-efficient-with-some-padding 3 anchor.	3 / 5
Actionability	All four quick-start examples (OLS, Logit, ARIMA, GLM) are complete, copy-paste ready with correct statsmodels imports, and cover the common cases including prediction intervals, odds ratios, marginal effects, AUC, and an overdispersion→Negative Binomial fallback, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	Four numbered workflows give clear sequences with implicit checkpoints (check diagnostics, check overdispersion), but they lack explicit 'if X fails, do Y' feedback loops; this fits the clear-sequence-with-minor-validation-gaps 4 anchor rather than the explicit-feedback-loop 5 anchor.	4 / 5
Progressive Disclosure	The SKILL.md overview points to five clearly signaled, one-level-deep reference files that all exist in references/, with content appropriately split; the duplicated 'Reference Documentation' section is a minor organization gap keeping it just below the clean 5 anchor.	4 / 5
	Total	16 / 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 distinctive with excellent capability coverage and natural trigger terms, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Adding a concrete trigger phrase would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. 'Use when fitting regression or time series models, running hypothesis tests, or performing econometric inference.'

Add a couple of common synonyms/extension triggers users say (e.g. 'regression', 'p-values', 'ANOVA') to round out trigger term coverage.

Consider framing capabilities as verb-actions (e.g. 'Fit, diagnose, and compare...') to strengthen the 'what' phrasing.

Dimension	Reasoning	Score
Specificity	The description lists many concrete capabilities ('OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC'), providing comprehensive coverage of the statistical modeling domain, matching the 5-anchor example of multiple specific concrete actions.	5 / 5
Completeness	It has a clear 'what' (statistical modeling toolkit with named methods) but lacks an explicit 'Use when...' clause; the trailing 'for rigorous statistical inference and econometric analysis' only weakly implies when, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural keyword coverage ('OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC') that practitioners would say, but missing common synonyms and file extensions (no 'regression', 'p-values', or extension triggers), so it falls just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The specific model roster (OLS, GLM, ARIMA, AIC/BIC, econometric analysis) carves a clear, distinct niche with minimal overlap against general data-wrangling or ML skills, matching the clear-niche 5 anchor.	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 (609 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/statsmodels/SKILL.md
Commit: ddcaa2a

Reviewed: 6 days 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.