experimental-data-analysis

Statistical analysis and reporting for experimental datasets; use when you need to interpret experimental results, test significance (t-tests/ANOVA), or generate reproducible reports.

Quality

68%

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/experimental-data-analysis/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 content is well-organized with real reference files and a clear run-based workflow, but it over-claims relative to what the bundled scripts actually implement and lacks explicit validation/feedback checkpoints in the workflow. Reducing the Key Features/Implementation Details overlap would also improve token efficiency.

Suggestions

Align the described analysis scope with the scripts: either extend analyze_experiment.py to support multi-way ANOVA, post-hoc Tukey, effect sizes, confidence intervals, non-parametric tests, and assumption checks, or narrow the body's claims to what the scripts actually perform.

Add explicit validation/feedback checkpoints to the workflow, and reorder assumption checks (normality, homogeneity of variance) to occur before inferential testing rather than as a final step.

Consolidate the overlapping 'Key Features' and 'Implementation Details' coverage of descriptive/inferential statistics and reporting to remove redundancy and tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basics Claude knows, but 'Key Features' and 'Implementation Details' substantially overlap (both cover descriptive stats, inferential testing, assumption checks, reporting), which is unnecessary duplication that could be tightened — anchor 3 rather than the minor-trim anchor 4.	3 / 5
Actionability	Concrete executable commands are present ('python scripts/init_run.py', 'python scripts/analyze_experiment.py'), but the scripts only implement descriptive stats, t-tests, and one-way ANOVA, while the body promises multi-way ANOVA, Tukey post-hoc, effect sizes, CIs, non-parametric alternatives, and assumption checks — key executable details are missing relative to the described scope, fitting anchor 3.	3 / 5
Workflow Clarity	A clear sequenced pipeline and run-directory conventions exist, but validation checkpoints and feedback loops are only implicit, and assumption checks are sequenced as step 4 (after inferential testing in step 3) rather than before — for a batch report-generation operation the missing explicit validation caps this at anchor 3.	3 / 5
Progressive Disclosure	Good structure with real, clearly-signaled one-level-deep references ('references/stats-method-selection.md', 'references/reporting-template.md') and scripts kept separate from the overview, but the reference navigation is a bullet list rather than dedicated sections and the inline Implementation Details is somewhat dense, fitting anchor 4 rather than anchor 5.	4 / 5
	Total	13 / 20 Passed

Description

83%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 is strong: it clearly states both the capability and concrete usage triggers with natural keywords, and carves out a recognizable niche in experimental statistical analysis. Minor improvements would be adding a few more synonyms/file types and tightening coverage of the full analysis scope.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('test significance (t-tests/ANOVA)', 'interpret experimental results', 'generate reproducible reports', 'Statistical analysis and reporting') but leaves minor gaps such as descriptive statistics and assumption checks, fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Statistical analysis and reporting for experimental datasets') and when ('use when you need to interpret experimental results, test significance (t-tests/ANOVA), or generate reproducible reports') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('experimental results', 'test significance', 't-tests/ANOVA', 'reproducible reports') that users would say, though a few common terms like 'p-values', 'effect size', or 'CSV' are missing, matching anchor 4.	4 / 5
Distinctiveness Conflict Risk	The experimental-statistics niche with triggers like t-tests/ANOVA and significance testing is mostly distinct with only minor overlap risk against general data-analysis skills, fitting anchor 4 rather than the fully-distinct anchor 5.	4 / 5
	Total	17 / 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/experimental-data-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~2 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.