scientist

Standard data analysis - comprehensive statistical analysis (Sonnet-tier)

Quality

61%

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 ./skills/scientist/SKILL.md

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 concise and action-oriented with real scipy/sklearn code and an explicit quality-gate spec, but the examples are not fully runnable (undefined helper variables) and the stated quality gate is not actually demonstrated in the output (Sample Size is missing). Structure is clean and appropriately self-contained.

Suggestions

Define the helper variables used in the examples (pooled_std, ci_lower, ci_upper) or compute them inline so the snippets are copy-paste runnable.

Make the code honor the stated quality gate by also printing Sample Size, so the "MUST include" checklist is fully demonstrated.

Tighten the opening by trimming the role line and merging the capabilities list into the worked examples to remove redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean: a short capabilities list, a tight quality-gate spec, and mostly self-explanatory code without explaining what scipy/sklearn or p-values are, fitting the score-4 anchor "Efficient; minor instances of over-explanation that could be trimmed"; it is not a 5 because the "You are Scientist" role line and the redundant capabilities list add slight padding.	4 / 5
Actionability	Real executable code is provided for a t-test and linear regression with concrete output formatting, matching the score-4 anchor "Mostly executable guidance; concrete code or commands with minor gaps"; it is not a 5 because pooled_std, ci_lower, and ci_upper are referenced but never defined, so the snippet is not fully copy-paste runnable.	4 / 5
Workflow Clarity	A quality-gate checklist ("Every finding MUST include: CI, Effect Size, P-value, Sample Size") acts as an implicit checkpoint, but there is no sequenced workflow or validate-fix-retry loop, and the code omits Sample Size so the gate is not honored, fitting the score-3 anchor with validation gaps; it is not a 4 because the checkpoint is not actually demonstrated in the examples.	3 / 5
Progressive Disclosure	The skill is a single well-organized file with clear sections (Capabilities, Quality Standards, Regression Analysis) and no nested or buried references, and there are no bundle files to navigate, so the simple-skill exception applies; it is not a 4 because organization is clean and there are no structural gaps to trim.	5 / 5
	Total	16 / 20 Passed

Description

32%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 generic and activation-poor: it names a broad domain without concrete actions, user-facing trigger phrases, or a Use-when clause, and the "(Sonnet-tier)" tag is internal metadata rather than a trigger. It would not reliably drive correct skill activation.

Suggestions

Replace generic phrasing with concrete actions, e.g. "Runs hypothesis tests, correlation and regression analysis on tabular data and reports effect sizes, p-values, and confidence intervals."

Add an explicit trigger clause such as "Use when the user asks for statistical analysis, hypothesis testing, or regression on a dataset."

Drop the "(Sonnet-tier)" qualifier from the description; it is routing metadata, not a user-facing trigger term.

Dimension	Reasoning	Score
Specificity	The description "Standard data analysis - comprehensive statistical analysis (Sonnet-tier)" names the domain (statistical analysis) but lists no concrete actions, matching the score-2 anchor "Names the domain but actions are minimal or generic"; it is not a 3 because no specific operations (e.g., hypothesis testing, regression) are stated.	2 / 5
Completeness	It offers only a vague "what" ("Standard data analysis - comprehensive statistical analysis") and no "when"/Use-when clause, matching the score-2 anchor "Has a vague 'what' and no 'when'"; it is not a 3 because the what is too generic to be a clear statement of function.	2 / 5
Trigger Term Quality	"data analysis" and "statistical analysis" are a couple of relevant, somewhat natural keywords, but common variations/synonyms and file-type triggers are absent, fitting the score-3 anchor; it is not a 4 because coverage is thin and "(Sonnet-tier)" is internal jargon rather than a user trigger.	3 / 5
Distinctiveness Conflict Risk	"Standard data analysis" is very broad with high overlap risk against many analytics skills, aligning with the score-2 anchor; it is not a 3 because "statistical analysis" alone does not carve out a niche specific enough to meaningfully reduce conflict risk.	2 / 5
	Total	9 / 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: TurnaboutHero/oh-my-antigravity
Path: skills/scientist/SKILL.md
Commit: f73e1ff

Reviewed: 15 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.