Name: statsmodels
Rating: 52 (1 reviews)
Author: administrakt0r

statsmodels

Statsmodels is Python's premier library for statistical modeling, providing tools for estimation, inference, and diagnostics across a wide range of statistical methods.

Quality

60%

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/AI-Agents-Safe-Coding-Skills-claude/skills/statsmodels/SKILL.md

The canonical home for this skill is statsmodels in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

67%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 a strong, action-oriented skill file with executable code across the main statsmodels workflows and clear navigation to reference files. Its main weakness is verbosity in the capability catalogs, which restate concepts Claude already knows and overlap with the referenced files.

Suggestions

Trim the explanatory 'Core Statistical Modeling Capabilities' catalogs (per-family and per-test descriptions that restate known concepts) and defer that detail to the reference files, keeping SKILL.md as an overview.

Define or annotate the placeholder input variables (X_data, y, y_series, y_binary, df) so the code examples are closer to fully copy-paste runnable.

Make workflow validation explicit with feedback loops (e.g., 'if residual diagnostics fail, refit with robust SEs and re-check') instead of only implicit conditionals, and ensure the referenced reference/*.md files actually exist in the bundle.

Dimension	Reasoning	Score
Conciseness	Dense, executable code blocks earn their tokens, but the 'Core Statistical Modeling Capabilities' catalogs restate concepts Claude already knows (per-distribution-family and per-test descriptions), making it mostly efficient with padded sections per anchor 3.	3 / 5
Actionability	Concrete, near-copy-paste code is given for OLS, Logit, ARIMA, GLM, the formula API, model comparison, and cross-validation, but examples rely on undefined placeholder inputs (X_data, y, y_series), a minor gap keeping it at anchor 4 rather than 5.	4 / 5
Workflow Clarity	Four well-sequenced numbered workflows include conditional checkpoints (e.g., 'check overdispersion -> if overdispersed, fit Negative Binomial'; 'test stationarity -> difference if non-stationary'), giving a clear sequence with most checkpoints present per anchor 4; the operations are not destructive/batch so the cap-3 rule does not apply.	4 / 5
Progressive Disclosure	Clear section structure with one-level-deep reference pointers in each capability section plus a dedicated 'Reference Documentation' navigation section; the minor gap is that inlined capability catalogs overlap the (absent) reference files, fitting anchor 4 rather than the cleanly split anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

53%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 conveys a clear capability domain and names a specific library, but relies on generic action verbs and a marketing buzzword, and omits any explicit 'Use when...' trigger guidance. It is competent but not comprehensive or trigger-optimized.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger scenarios (e.g., fitting regression models, ARIMA/time-series forecasting, running hypothesis or diagnostic tests, econometric inference) to satisfy the 'when' and add natural trigger terms.

Replace the marketing phrase 'Python's premier library' with concrete capability verbs and list more specific actions (OLS/GLM regression, ARIMA forecasting, robust standard errors, model comparison via AIC/BIC) to lift specificity.

Include natural synonyms users actually say (regression, logistic regression, ARIMA, hypothesis tests, panel/econometric models) so the description matches how the skill would be requested.

Dimension	Reasoning	Score
Specificity	Names the domain ('statistical modeling') and a few actions ('estimation, inference, and diagnostics'), but they are high-level and padded by the buzzword 'premier', fitting anchor 3 rather than the more comprehensive anchor 4.	3 / 5
Completeness	It has a clear 'what' (Python library for statistical modeling with estimation/inference/diagnostics tools) but no 'Use when...' clause or explicit trigger guidance, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Core terms ('statistical modeling', 'estimation', 'inference', 'diagnostics') are present but technical, and common natural synonyms a user would say (regression, time series, ARIMA, hypothesis testing, econometrics) are missing, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	Naming a specific library ('Statsmodels') with a clear statistical-modeling niche makes it mostly distinct, with only minor overlap risk against general stats/scipy skills, fitting anchor 4.	4 / 5
	Total	13 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (615 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	12 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/statsmodels/SKILL.md
Commit: 731a928

Reviewed: 17 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.