scientist
Standard data analysis - comprehensive statistical analysis (Sonnet-tier)
42
Quality
26%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/scientist/SKILL.mdQuality
Discovery
14%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 description is too vague and generic to effectively guide skill selection. It lacks concrete actions, explicit trigger conditions, and distinctive language that would differentiate it from other data-related skills. The '(Sonnet-tier)' qualifier appears to be internal metadata rather than useful selection criteria.
Suggestions
Add specific concrete actions like 'Performs regression analysis, hypothesis testing, descriptive statistics, and correlation analysis on datasets'
Include an explicit 'Use when...' clause with trigger terms like 'statistics', 'mean', 'standard deviation', 'p-value', 'CSV analysis', 'data summary'
Specify what distinguishes this from other data skills - mention supported file types, specific statistical methods, or output formats to reduce conflict risk
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'comprehensive statistical analysis' without listing any concrete actions. It doesn't specify what statistical methods, operations, or outputs the skill provides. | 1 / 3 |
Completeness | The description only vaguely addresses 'what' (statistical analysis) and completely lacks any 'when' clause or explicit trigger guidance. The '(Sonnet-tier)' qualifier is internal jargon, not user-facing guidance. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords ('data analysis', 'statistical analysis') that users might say, but lacks common variations like 'stats', 'analytics', 'regression', 'correlation', specific file types, or tool names. | 2 / 3 |
Distinctiveness Conflict Risk | 'Data analysis' and 'statistical analysis' are extremely broad terms that would conflict with many other skills involving data, spreadsheets, visualization, or any quantitative work. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a decent starting template for statistical analysis output formatting but falls short of being a comprehensive guide. The code examples demonstrate output structure but are incomplete and lack the workflow guidance needed for proper statistical analysis (assumption checking, method selection, result validation).
Suggestions
Complete the code examples by defining all variables (pooled_std, ci_lower, ci_upper) and including necessary imports
Add a workflow section explaining when to use t-tests vs regression vs other methods, including assumption checks (normality, homoscedasticity)
Remove the persona framing and capabilities list - focus on actionable guidance Claude can execute
Add validation checkpoints for statistical assumptions before running tests (e.g., check normality before t-test)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary elements like the persona framing ('You are Scientist'), the capabilities list that Claude already knows, and the closing quote. The code examples are lean but the surrounding content could be tightened. | 2 / 3 |
Actionability | Provides executable code snippets but they're incomplete - 'pooled_std', 'ci_lower', 'ci_upper' are undefined in the first example. The regression example is more complete but still assumes data preparation is done. Missing imports like numpy/pandas. | 2 / 3 |
Workflow Clarity | No clear workflow sequence for conducting analysis. Lists capabilities and shows isolated code snippets but doesn't explain when to use which technique, how to validate results, or how to handle edge cases like non-normal distributions or multicollinearity. | 1 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections (Quality Standards, Regression Analysis), but for a 'comprehensive statistical analysis' skill, there are no references to additional resources for advanced topics, assumption checking, or visualization guidance mentioned in capabilities. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- TurnaboutHero/oh-my-antigravity
- Commit
fab464f
- 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.