scientist-low

Basic data analysis - fast exploratory analysis (Haiku-tier)

Quality

66%

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-low/SKILL.md

Quality

Content

93%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 lean, fully executable, and well-organized for a simple exploratory-analysis skill, with concrete code covering the common cases and no padding. The only minor gap is the absence of an explicit step sequence, which is acceptable for a single-purpose REPL skill.

Dimension	Reasoning	Score
Conciseness	The body is lean: short section headers, minimal prose, and copy-paste code with no over-explanation of pandas or matplotlib concepts Claude already knows, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'. Not a 4 because there are essentially no padded sentences to trim.	5 / 5
Actionability	It provides fully executable Python covering the common cases (load via read_csv, describe, structured output markers, and a complete matplotlib savefig example), matching 'Fully executable; copy-paste ready code; specific examples cover the common cases'. Not a 4 because there are no meaningful execution gaps.	5 / 5
Workflow Clarity	As a simple single-purpose REPL skill the load-then-inspect-then-visualize flow is unambiguous, but there are no explicit sequencing or validation checkpoints, so it sits just below the simple-skill 5 anchor. Not a 5 because no checklist or explicit step sequence is given, and not a 3 because the single action is clear and non-destructive so no validation is required.	4 / 5
Progressive Disclosure	It is a short, single-purpose skill with well-organized sections (Use Cases, Persistent REPL, Output Format, Visualization) and no need for external reference files, so per the simple-skill note it earns a 5 for clear organization with easy navigation. Not a 4 because nothing is misplaced or buried.	5 / 5
	Total	19 / 20 Passed

Description

25%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 too vague and generic to reliably drive activation: it names data analysis without concrete actions or trigger phrases and lacks any 'Use when' guidance. It is broadly distinguishable only by specialty, not by stated capabilities.

Suggestions

Replace 'Basic data analysis' with concrete actions, e.g. 'Load CSV/DataFrames, compute descriptive statistics, and generate quick visualizations for exploratory analysis'.

Add an explicit trigger clause such as 'Use when the user wants fast exploratory data analysis, summary statistics, or quick visualizations of a dataset'.

Include natural trigger terms users actually say (e.g. 'data exploration', 'EDA', 'summary statistics', '.csv') and clarify the niche to reduce overlap with other analytics skills.

Dimension	Reasoning	Score
Specificity	The phrase 'Basic data analysis' names the domain but offers only minimal, generic actions with no concrete verbs, matching the score-2 anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no 1-2 concrete actions (e.g. 'computes summary statistics', 'plots distributions') are stated.	2 / 5
Completeness	It gives only a vague 'what' ('Basic data analysis - fast exploratory analysis') and no 'when'/'Use when' trigger clause at all, fitting 'Has a vague what and no when'. Not a 3 because the 'what' is too generic to count as a clear capability statement.	2 / 5
Trigger Term Quality	Only the generic keyword 'data analysis' appears; natural user phrases like 'data exploration', 'summary statistics', 'EDA', or file types (.csv, .xlsx) are missing, matching 'One or two generic keywords; missing the natural phrases users say'. Not a 3 because common variations/synonyms are absent.	2 / 5
Distinctiveness Conflict Risk	'Basic data analysis' is very broad and would overlap with many analytics/statistics skills, matching 'Very broad; high overlap risk with many similar skills'. Not a 3 because nothing narrows it to a distinct niche.	2 / 5
	Total	8 / 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-low/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.