data-stats-analysis

Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

Quality

64%

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 ./scientific-skills/Data Analysis/data-stats-analysis/SKILL.md

Quality

Content

63%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 highly actionable with thorough executable examples and a clear stepwise workflow including some validation checkpoints, but it is a long monolithic file that could be split into references and is padded with decorative prints and repeated marketing. Progressive disclosure is the weakest dimension because no detailed material is factored out.

Suggestions

Move the domain-specific Common Use Cases (differential gene expression, cluster enrichment, batch effect detection) and Advanced Features into separate reference files linked one level deep from the main body.

Trim decorative emoji print statements and the repeated 'ALL LLM providers' marketing from Overview and Technical Notes to reduce token cost.

Add an explicit validate-then-proceed loop for batch/multiple-testing workflows (e.g., check assumptions, only interpret p-values when validation passes) to push workflow clarity higher.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful executable code, but it is padded with decorative emoji print statements (✅/❌/⚠️), repeated "ALL LLM providers" marketing in both Overview and Technical Notes, and verbose interpretation if/else blocks that could be tightened; it is efficient at its core but noticeably longer than necessary.	3 / 5
Actionability	Provides concrete, executable Python with complete functions (cohens_d, calculate_confidence_interval) covering common cases, but examples rely on undefined input variables (group1, gene_expression_df) and include no data-loading step, leaving minor gaps before copy-paste readiness.	4 / 5
Workflow Clarity	A clear Step 1–6 sequence is present with some validation checkpoints (Levene's test branching to Welch's t-test, normality testing recommending non-parametric alternatives), plus troubleshooting and an Input Validation section, but it lacks explicit validate-then-proceed feedback loops for the batch/multiple-testing operations.	4 / 5
Progressive Disclosure	No bundle files exist, so everything (Advanced Features, three large genomics Common Use Cases, Troubleshooting) is inlined in one ~490-line SKILL.md rather than split into one-level-deep reference files; section headers provide structure, but content that should be separate is inline.	3 / 5
	Total	14 / 20 Passed

Description

66%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.

The description clearly states concrete capabilities and the libraries used, but it is missing an explicit 'Use when...' trigger and pads in a generic LLM-provider compatibility claim that does not aid activation. Trigger-term coverage is good but not comprehensive.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g., 'Use when the user asks for t-tests, ANOVA, p-values, correlations, or multiple-testing corrections.'

Drop the 'Works with ANY LLM provider' line from the description; it is compatibility marketing, not an activation signal, and adds no trigger value.

Include natural trigger terms users actually say (t-test, ANOVA, p-value, confidence interval) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels"), but omits capabilities present in the body (confidence intervals, effect size, non-parametric tests), so coverage has minor gaps rather than being comprehensive.	4 / 5
Completeness	The "what" is clear ("Perform statistical tests... multiple testing corrections"), but there is no "Use when..." clause or equivalent trigger guidance; "Works with ANY LLM provider" is a compatibility claim, not a usage trigger, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Good keyword coverage with natural phrases like "statistical tests", "hypothesis testing", "correlation analysis", and library names (scipy, statsmodels), but common variations users say (t-test, ANOVA, p-value) are missing, falling short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	The scipy/statsmodels statistical-testing niche is mostly distinct with minimal conflict risk, but the absence of explicit trigger phrases and the generic "ANY LLM provider" marketing leave minor overlap risk with related data-analysis skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/data-stats-analysis/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.