statistical-analysis
Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.
74
50%
Does it follow best practices?
Impact
91%
1.13xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/statistical-analysis/SKILL.mdQuality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
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 actionable code examples and comprehensive APA reporting templates, making it highly practical for statistical analysis tasks. However, it is far too verbose—much of the content explains concepts Claude already knows (statistical principles, when to use tests, common pitfalls) and inline content duplicates what should be in the referenced files. Trimming the body to a concise overview with pointers to the reference files would dramatically improve token efficiency.
Suggestions
Move detailed code examples (regression diagnostics, Bayesian t-test, full ANOVA workflow) into the referenced files (e.g., references/test_selection_guide.md) and keep only one brief example in SKILL.md as a quick-start.
Remove sections that explain concepts Claude already knows: 'Common Pitfalls to Avoid', 'Best Practices' list, 'Key Advantages' of Bayesian methods, 'When to Use This Skill', textbook recommendations, and explanatory sentences like 'Effect sizes quantify magnitude, while p-values only indicate existence of an effect.'
Add explicit validation checkpoints in the workflow, e.g., 'If assumption check fails → switch to non-parametric path' as a concrete branching step rather than a separate section to read.
Reduce the SKILL.md to ~100-150 lines: a quick-start example, the test selection quick reference table, one compact code example, and well-signaled links to the reference files for everything else.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Explains concepts Claude already knows (what effect sizes are, what p-values mean, when to use Bayesian methods, basic statistical concepts). Sections like 'Common Pitfalls to Avoid', 'Best Practices', 'When to Use This Skill', and 'Key Advantages' of Bayesian methods are largely things Claude already understands. The 'Support and Further Reading' section with textbook recommendations adds no value for Claude. Much content could be cut or moved to reference files. | 1 / 3 |
Actionability | Provides fully executable Python code examples for t-tests, ANOVA, regression, Bayesian analysis, power analysis, and assumption checking. Code is copy-paste ready using real libraries (pingouin, statsmodels, pymc, arviz). APA report templates are concrete and complete with specific formatting. | 3 / 3 |
Workflow Clarity | The decision tree and getting-started checklist provide a clear sequence, and the assumption checking workflow includes a validation step before proceeding. However, the decision tree uses vague 'See section X' references rather than concrete steps, and there's no explicit error recovery or feedback loop for when analyses fail or produce unexpected results. The checklist is good but lacks validation checkpoints between steps. | 2 / 3 |
Progressive Disclosure | References to external files (references/*.md, scripts/*.py) are well-signaled and one level deep, which is good. However, the SKILL.md itself is monolithic with enormous amounts of inline content that should be in those reference files. The test selection guide, full regression diagnostic code, Bayesian analysis examples, and APA templates could all live in the referenced files, keeping SKILL.md as a lean 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 (631 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
cbcae7b
- 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.