statsmodels

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

Quality

81%

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

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.

A comprehensive, highly actionable skill body with copy-paste-ready code and well-sequenced workflows backed by real reference files. Its main weakness is duplication between the inlined Core Capabilities sections, the Reference Documentation summary, and the reference files themselves, which hurts both conciseness and progressive disclosure.

Suggestions

Trim the Core Capabilities bullet lists (lines 180-341) to a brief model-type overview and rely on the reference files for the per-family detail, removing the duplication flagged in conciseness.

Replace the Reference Documentation per-file summaries (lines 526-572) with a single concise table of file + one-line purpose to avoid restating each reference's contents.

Add an explicit validate-then-fix feedback loop to at least one workflow (e.g., Workflow 1: 'If heteroskedasticity test is significant, refit with robust SEs and re-check') to lift workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence with no padding of basic concepts, but the ~160-line Core Capabilities bullet lists and the Reference Documentation re-summary duplicate content already in the reference files, so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready code across OLS, Logit, ARIMA, GLM, formula API, AIC/BIC comparison, LR test, and cross-validation, with real imports and method calls covering the common cases.	5 / 5
Workflow Clarity	Four clearly sequenced numbered workflows with validation checkpoints present (residual diagnostics, stationarity tests, out-of-sample/CV evaluation), but no explicit error-recovery feedback loops, which is the score-5 differentiator.	4 / 5
Progressive Disclosure	Well-signaled one-level-deep references to five real reference files linked inline and re-indexed with grep patterns, but the SKILL.md body inlines the model-family bullet lists and a per-reference summary that partly duplicate the reference files.	4 / 5
	Total	16 / 20 Passed

Description

87%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 strong, well-structured description that concretely names model classes and diagnostics, provides an explicit 'Use when' trigger, and proactively disambiguates from a sibling skill. Minor specificity and synonym coverage gaps keep trigger-term quality and specificity at 4 rather than 5.

Suggestions

Add a couple of natural synonyms/verbs users say (e.g., 'regression', 'fit a model') to round out trigger-term coverage.

Reframe one or two model-class names as concrete verbs (e.g., 'Fit OLS/GLM/ARIMA models and produce diagnostics') to push specificity from 4 to 5.

Dimension	Reasoning	Score
Specificity	Lists several specific concrete capabilities (OLS, GLM, mixed models, ARIMA with diagnostics, residuals, inference, coefficient tables), but frames them as model-class names rather than a fully enumerated set of actions, leaving minor coverage gaps.	4 / 5
Completeness	Clearly states what the skill does (statistical models library with diagnostics, residuals, inference) and explicitly states when to use it via a concrete 'Use when you need specific model classes...' trigger phrase.	5 / 5
Trigger Term Quality	Includes strong natural terms a user would say (OLS, GLM, ARIMA, econometrics, time series, diagnostics, residuals), but omits some common synonyms and file extensions, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (rigorous statistical modeling/econometrics) and explicitly routes APA test-selection work to the sibling statistical-analysis skill, actively minimizing conflict.	5 / 5
	Total	18 / 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 (618 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

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/statsmodels/SKILL.md
Commit: 3a6c3a9

Reviewed: about 21 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.