data-scientist

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.

Quality

31%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/data-scientist/SKILL.md

The canonical home for this skill is data-scientist in rmyndharis/antigravity-skills

Quality

Content

17%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 a verbose persona/capability catalog that adds little beyond what Claude already knows, with no executable guidance, no validation checkpoints, and no progressive disclosure via bundle files. It reads as a resume rather than an actionable skill.

Suggestions

Cut the exhaustive tool/algorithm enumerations and Behavioral Traits/Knowledge Base restatements; keep only guidance Claude would not already know (project-specific conventions, preferred stacks, decision rules).

Add concrete, executable guidance: code snippets, exact commands, or specific step-by-step procedures for the most common tasks (e.g., an A/B test analysis or churn modeling template).

Introduce validation checkpoints in the workflow (e.g., 'validate assumptions before modeling', 'check for data leakage after train/test split') and move the long capability lists into reference files under references/.

Dimension	Reasoning	Score
Conciseness	The body is a ~190-line persona dump enumerating tools and algorithms (e.g., 'pandas, NumPy, scikit-learn', 'ARIMA, Prophet', 'CNNs, RNNs, LSTMs, transformers') that Claude already knows, with padded Behavioral Traits and Knowledge Base sections restating common concepts.	2 / 5
Actionability	There is no executable code, commands, or concrete procedural guidance; the Instructions are abstract ('Apply relevant best practices and validate outcomes') and the body describes capabilities rather than instructing action.	1 / 5
Workflow Clarity	The 'Response Approach' lists eight numbered steps, but they are high-level and abstract ('Understand business context', 'Explore data thoroughly') with no concrete commands, no validation checkpoints, and no feedback loops.	2 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the entire capability catalog is inlined into one monolithic SKILL.md; the content that clearly belongs in separate reference files is not split out.	2 / 5
	Total	7 / 20 Passed

Description

45%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 a clear but generic role statement that answers 'what' without any explicit 'when to use' guidance. It leans on domain labels rather than concrete, distinctive trigger phrases.

Suggestions

Add an explicit 'Use when ...' clause naming concrete user triggers (e.g., 'Use when the user asks to build a predictive model, design an A/B test, forecast a time series, or analyze a dataset').

Replace generic verbs like 'Handles' with specific actions ('Forecasts', 'Segments customers', 'Trains and evaluates classifiers') to lift specificity.

Add natural synonyms and tool/file cues users actually say ('regression', 'churn model', 'feature engineering') to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Expert data scientist') and several sub-domains ('advanced analytics, machine learning, and statistical modeling', 'complex data analysis, predictive modeling, and business intelligence'), but the verbs ('Handles') are generic and these are categories rather than concrete actions like 'extract' or 'forecast'.	2 / 5
Completeness	It clearly states the 'what' (a data scientist handling analytics, ML, modeling, BI), but provides no explicit 'when' trigger guidance; per the rubric, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant keywords a user might say ('machine learning', 'statistical modeling', 'predictive modeling', 'business intelligence'), but it lacks natural trigger phrasing and common synonyms/variations, and offers no 'Use when...' style framing.	3 / 5
Distinctiveness Conflict Risk	'Expert data scientist' is a recognizable niche, but the broad accompanying terms ('data analysis', 'business intelligence', 'analytics') create overlap risk with adjacent BI/analytics skills rather than a clearly distinct trigger set.	3 / 5
	Total	11 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/data-scientist/SKILL.md
Commit: 57c135b

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.