statistics-math

Statistics, probability, linear algebra, and mathematical foundations for data science

Quality

57%

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 ./bundled/skills/statistics-math/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, executable statistics cookbook with high actionability, but it is presented as a single dense page with no links to the bundled references and includes some tutorial-style padding Claude does not need. Sequencing and progressive disclosure are the main weak spots.

Suggestions

Replace tutorial demonstrations (CLT demo, regularization comparison) with minimal focused snippets or move them to a reference file.

Link the existing bundle files from the body, e.g. add a '## Patterns & Validation' section pointing to references/PATTERNS.md and scripts/validate.py.

Add an explicit pre-test checklist (check normality/assumptions, then interpret p-value) to give the hypothesis-testing workflow a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight executable code, but several blocks teach concepts Claude already knows (a 'Central Limit Theorem demonstration', a full OLS/Ridge/Lasso regularization comparison) adding tutorial padding rather than just the needed recipe, so it is efficient-with-some-unweight rather than the every-token-earns-its-place level 3.	2 / 3
Actionability	Every section provides fully executable, copy-paste-ready Python with real libraries (numpy, scipy, statsmodels, sklearn) and concrete worked examples like the two-proportion z-test and matrix operations, matching the 'fully executable code, specific examples' anchor.	3 / 3
Workflow Clarity	The content is a set of independent recipes with no sequenced multi-step process or validation checkpoints; for a recipe collection that is acceptable structure, but it never provides an explicit validate-then-proceed loop (e.g. checking test assumptions before interpreting a p-value), so it sits at the 'sequence present but checkpoints implicit' level rather than 3.	2 / 3
Progressive Disclosure	SKILL.md is monolithic with all content inline, and although bundle files exist (references/GUIDE.md, references/PATTERNS.md, scripts/validate.py), the body never references them and those files are generic boilerplate disconnected from the actual statistics material, so structure exists but navigation/signaling is weak rather than the clean one-level-deep reference pattern of level 3.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 a concise, third-person subject-area statement that names the right domains but stops short of stating concrete actions or explicit use-when triggers. It is functional but reads as a category label rather than invocation guidance.

Suggestions

Add concrete actions, e.g. 'Performs descriptive statistics, hypothesis tests, A/B tests, and regression analysis'.

Add an explicit trigger clause such as 'Use when the user needs statistical analysis, probability calculations, or linear algebra for data-science tasks'.

Sharpen distinctiveness by scoping away from ML/DL, e.g. 'Foundational math (not model building) — see machine-learning for modeling'.

Dimension	Reasoning	Score
Specificity	The phrase 'Statistics, probability, linear algebra, and mathematical foundations for data science' names several concrete domains but lists no actions (it describes a subject area rather than what the skill does), landing at the 'names domain but not comprehensive' level rather than the action-listing level 3 or the fully vague level 1.	2 / 3
Completeness	It states what the skill covers (the math domains) but provides no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	'Statistics, probability, linear algebra' are natural terms a user might say, but common task-level variations a user would actually invoke (e.g. hypothesis test, A/B test, regression, p-value) are absent, so coverage is partial rather than the broad natural-term spread of level 3.	2 / 3
Distinctiveness Conflict Risk	The stats/probability/linear-algebra framing is somewhat specific, but 'mathematical foundations for data science' overlaps with sibling skills the frontmatter itself unlocks (machine-learning, deep-learning, data-engineering), so it could still trigger for a related skill.	2 / 3
	Total	8 / 12 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/statistics-math/SKILL.md
Commit: f627ab5

Reviewed: 3 days 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.