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.

Quality

82%

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

Quality

Content

72%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 and well-structured for progressive disclosure, with real bundle files backing every reference. It is let down by verbosity in concept-restating sections and by advisory rather than enforced validation checkpoints in the analysis workflow.

Suggestions

Move or cut concept-restating prose (e.g., 'Effect sizes quantify magnitude, while p-values only indicate existence', 'Key Advantages', 'Common Pitfalls', textbook lists) to keep the body lean; Claude already knows these.

Turn assumption checking into an explicit validate-fix-retry feedback loop (check → on violation apply the listed remediation → re-check before proceeding) so workflow_clarity reflects a real checkpoint rather than a recommendation.

Consolidate the duplicate 'Support and Further Reading' reference list with the earlier Resources section to avoid restating the same file pointers twice.

Dimension	Reasoning	Score
Conciseness	Code blocks are efficient, but several sections pad the body with content Claude already knows (effect-size aphorisms, 'Key Advantages', 'Common Pitfalls', textbook lists) and could be trimmed or moved to references.	3 / 5
Actionability	Copy-paste-ready, executable code for t-test, ANOVA, regression, Bayesian t-test, and power analysis, plus concrete assumption_checks.py function signatures and filled-in APA report templates covering the common cases.	5 / 5
Workflow Clarity	A decision tree and Getting Started Checklist sequence the work, but assumption failures are handled advisedly rather than via an enforced validate-fix-retry checkpoint, leaving validation gaps for data/batch operations.	3 / 5
Progressive Disclosure	Clear overview body with consistently signaled one-level-deep references (references/*.md and scripts/assumption_checks.py), a Resources section mapping each file, and content appropriately split across the bundle.	5 / 5
	Total	16 / 20 Passed

Description

92%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 specific, trigger-rich, and clearly distinguishes itself from programmatic modeling skills via an explicit boundary clause. It fully answers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Names multiple specific concrete actions — test selection, assumption checking, power analysis, and APA-formatted reporting — with comprehensive coverage of the skill's surface.	5 / 5
Completeness	Explicitly answers both 'what' (guided statistical analysis with test selection and reporting) and 'when' (Use when you need help choosing appropriate tests...) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('choosing appropriate tests', 'assumption checking', 'power analysis', 'APA-formatted results') but a few common synonyms a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Clear academic-statistics niche with an explicit boundary ('For implementing specific models programmatically use statsmodels'), giving minimal conflict risk with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (632 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/statistical-analysis/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.