statistical-analysis-advisor

Recommends appropriate statistical methods (T-test vs ANOVA, etc.) based.

Quality

53%

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/statistical-analysis-advisor/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 skill delivers solid actionable content—a working code example, parameter table, and well-signaled reference files—but is weighed down by large tracts of generic templated boilerplate and a workflow that is not tailored to the statistical domain. Trimming the boilerplate and grounding the workflow in real assumption-checking steps would meaningfully raise quality.

Suggestions

Remove or condense the generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Output Requirements, Response Template, Input Validation) that restate process guidance Claude already applies.

Rewrite the Workflow to reflect the actual statistical path—e.g., check data type/distribution and assumption validity before recommending a test, then verify power/sample size—instead of generic validate-and-deliver steps.

Resolve the undefined placeholders in the Usage example (group1, group2) so the code is copy-paste runnable end to end.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate Claude already knows ("validate the request... produce a bounded deliverable", templated Risk Assessment, Security Checklist, Evaluation Criteria, Response Template sections) alongside the useful domain content, making it noticeably verbose.	2 / 5
Actionability	Provides a concrete executable Python usage example (StatisticalAdvisor.recommend_test/check_assumptions/calculate_power), a real input-parameter table, and runnable commands (python -m py_compile, python scripts/main.py), with only minor gaps (undefined group1/group2 placeholders).	4 / 5
Workflow Clarity	A sequenced Workflow with explicit stop-early and fallback checkpoints exists, but the steps are generic process boilerplate rather than statistical-analysis-specific (no normality/assumption gating before test recommendation), leaving real validation gaps for the domain.	3 / 5
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references to the three real reference files (statistical_tests_guide.md, assumption_tests.md, power_analysis_guide.md) and scripts/main.py, with good organization though some inlined boilerplate could be trimmed.	4 / 5
	Total	13 / 20 Passed

Description

53%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 names a clear, distinct domain with recognizable trigger terms, but it is grammatically truncated and lacks any explicit "when to use" guidance, capping its completeness. It reads as a half-finished sentence rather than a polished trigger.

Suggestions

Complete the truncated sentence and add an explicit "Use when..." clause naming concrete triggers (e.g., "Use when choosing between a T-test, ANOVA, Chi-square, or non-parametric tests for a dataset").

Add natural-language synonyms users actually say ("hypothesis testing", "which statistical test", "sample size / power") to improve trigger-term coverage.

Expand the action list beyond "Recommends" to the concrete capabilities (assumption checking, power/sample-size calculation) for fuller specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (statistical methods) and one concrete action ("Recommends") with concrete examples ("T-test vs ANOVA, etc."), but coverage is limited to a single action and the sentence is truncated at "based.".	3 / 5
Completeness	It conveys a clear "what" (recommends statistical methods) but has no "Use when..." trigger guidance, and the sentence is cut off mid-phrase ("based."), so the cap at 3 for a missing when-clause applies.	3 / 5
Trigger Term Quality	"T-test" and "ANOVA" are natural terms a researcher would say, but broader natural phrases (statistical test, hypothesis testing, p-value, sample size) and synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	Statistical test recommendation is a fairly distinct niche anchored by "T-test vs ANOVA" triggers, with only minor overlap risk against general data-analysis skills.	4 / 5
	Total	13 / 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/statistical-analysis-advisor/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.