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.
85
75%
Does it follow best practices?
Impact
93%
1.09xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/statsmodels/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that clearly communicates specific capabilities (model classes, diagnostics, inference), includes rich natural trigger terms that users in statistics would use, and explicitly disambiguates from a related skill. The description is concise yet comprehensive, covering what, when, and how it differs from similar skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and model classes: OLS, GLM, mixed models, ARIMA, along with specific outputs like detailed diagnostics, residuals, inference, and coefficient tables. | 3 / 3 |
Completeness | Clearly answers both what ('Statistical models library for Python' with specific model classes and outputs) and when ('Use when you need specific model classes... Best for econometrics, time series, rigorous inference'). Also includes explicit disambiguation guidance pointing to statistical-analysis for a different use case. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'OLS', 'GLM', 'mixed models', 'ARIMA', 'econometrics', 'time series', 'inference', 'coefficient tables', 'residuals', 'diagnostics'. These are terms a user working in statistics would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishes itself from the related 'statistical-analysis' skill by specifying its niche (specific model classes, diagnostics, econometrics) versus guided test selection with APA reporting. The explicit disambiguation clause reduces conflict risk significantly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent executable code examples and good reference file organization, but is severely bloated with encyclopedic listings of model types, features, and capabilities that Claude already knows. The core Quick Start section is strong, but the surrounding content (~70% of the file) reads like a statsmodels documentation index rather than actionable guidance. Workflows lack explicit validation checkpoints and error recovery steps.
Suggestions
Cut the 'Core Statistical Modeling Capabilities' section drastically—move the detailed model/feature listings into the reference files and keep only a brief table or bullet list mapping outcome types to recommended models.
Reduce 'Common Pitfalls' to the top 5 most critical and non-obvious ones; Claude already knows basics like 'don't overfit' and 'check assumptions'.
Add explicit validation checkpoints and error-recovery branches to the workflows (e.g., 'If VIF > 10, remove or combine collinear predictors before proceeding').
Trim the 'Best Practices' section to only project-specific conventions that differ from standard statistical practice Claude already knows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensively lists model types, features, and capabilities that Claude already knows. The 'Core Statistical Modeling Capabilities' section is essentially a catalog of statsmodels features that adds little actionable value. The 'Common Pitfalls' list of 15 items, 'Best Practices' with 5 subsections, and 4 detailed workflows are largely general statistical knowledge Claude possesses. | 1 / 3 |
Actionability | The Quick Start examples are fully executable with proper imports, complete code blocks, and copy-paste ready snippets. Code covers OLS, Logit, ARIMA, GLM, formula API, model comparison, and cross-validation with concrete, runnable examples. | 3 / 3 |
Workflow Clarity | Four workflows are listed but they are high-level numbered lists without explicit validation checkpoints or feedback loops. For example, Workflow 1 says 'Check residual diagnostics' but doesn't specify what to do if diagnostics fail. The Quick Start code examples do include some inline validation (e.g., checking overdispersion and switching to NB), which partially compensates. | 2 / 3 |
Progressive Disclosure | References to 5 detailed reference files are well-organized and clearly signaled at the bottom. However, the SKILL.md itself contains massive amounts of content that should be in those reference files (e.g., the entire 'Core Statistical Modeling Capabilities' section with exhaustive model lists). The overview is not concise enough to serve as a true overview. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (613 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
899a51b
- 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.