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

76%

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 ./skills/statsmodels/SKILL.md

Quality

Content

53%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 well-organized hub that delegates detail to genuine one-level-deep reference files, but it is padded by a redundant reference-summaries section and offers only procedural checklists rather than inline executable examples or explicit validation feedback loops in its workflows.

Suggestions

Remove or condense the "Reference Documentation" section (lines 144-212); its per-file table-of-contents blurbs duplicate the links already provided in "Quick Start, Capabilities, and Model Selection".

Add one small inline executable example per workflow (e.g. an OLS fit + summary call) so the body is actionable without forcing a reference hop for the common case.

Reframe the workflow validation steps as explicit feedback loops (e.g. "Check residuals → if heteroskedasticity detected, refit with robust SEs → re-check") to make checkpoints explicit rather than implicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and task-oriented, but the "Reference Documentation" section (lines 144-212) re-summarizes each reference file's table of contents, duplicating the one-line links already given in "Quick Start, Capabilities, and Model Selection", and the 15-item pitfalls list could be trimmed.	3 / 5
Actionability	The body is an overview/index: the only inline executable snippets are `uv pip install statsmodels==0.14.6` and `rg` search patterns, while the four workflows are high-level checklists ("Fit initial OLS model", "Check residual diagnostics") without executable code, which lives in the reference files.	3 / 5
Workflow Clarity	Four workflows give clear numbered sequences with some implicit checkpoints (e.g. "If overdispersed, fit Negative Binomial"), but validation is listed as a step rather than framed as an explicit validate→fix→retry feedback loop, so checkpoints remain implicit.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references — all 8 linked files in references/ are real and organized by topic in the "Quick Start, Capabilities, and Model Selection" section; the minor gap is the redundant re-listing of those same references later in "Reference Documentation".	4 / 5
	Total	13 / 20 Passed

Description

100%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 description that concisely states what the skill does, when to use it via natural trigger terms, and where its boundary lies relative to a sibling skill. Third-person voice is maintained throughout with no vague filler.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference" plus "coefficient tables" — giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ("Statistical models library for Python... specific model classes... with detailed diagnostics, residuals, and inference") and when ("Use when you need specific model classes... Best for econometrics, time series") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Uses natural domain terms users actually say — "OLS, GLM, mixed models, ARIMA", "econometrics", "time series", "coefficient tables", "diagnostics" — with good synonym coverage across model families.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (rigorous inference / econometrics) and adds an explicit boundary — "For guided statistical test selection with APA reporting use statistical-analysis" — minimizing conflict with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/statsmodels/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.