Tessl • The management layer for AI agent skills

SkillPublic

data-scientist

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence. Use for data analysis tasks, ML modeling, statistical analysis, and data-driven insights.

Quality

53%

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/data-scientist/SKILL.md

Quality

Content

20%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 a persona résumé: an exhaustive enumeration of data-science knowledge Claude already possesses, with virtually no executable guidance, examples, or decision rules. The well-labeled 8-step response workflow and clear sectioning are the only structural strengths; nearly everything else should be deleted or moved to reference files.

Suggestions

Cut the Capabilities, Knowledge Base, and Behavioral Traits catalogs — Claude already knows these — and keep only the domain-specific conventions, tool preferences, or judgment calls that differ from default behavior.

Add concrete, executable guidance for the representative tasks, e.g., a short code/template for a churn model, an A/B test analysis, or a segmentation workflow with specific libraries and evaluation metrics.

Move any retained domain detail (e.g., the marketing/financial/operations analytics sub-sections) into one-level-deep files under references/ and link them from a concise SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Roughly 150 of the ~187 lines are an encyclopedic catalog of concepts Claude already knows ('Supervised learning: linear/logistic regression, decision trees, random forests, XGBoost', 'Python ecosystem: pandas, NumPy, scikit-learn'), which is exactly the heavy padding the level-1 anchor penalizes; only the small Use/Do-not-use and Response Approach sections carry information.	1 / 5
Actionability	There is no code, command, or concrete example anywhere in the body; instructions like 'Clarify goals, constraints, and required inputs' and 'Apply relevant best practices and validate outcomes' only describe an attitude rather than tell Claude what to execute, matching the 'entirely vague or abstract' level-1 anchor.	1 / 5
Workflow Clarity	The 8-step 'Response Approach' provides a coherent ordered sequence, and validation appears as a step ('Validate results rigorously through statistical testing and cross-validation'), but checkpoints are implicit and there are no concrete validate-fix-retry feedback loops, matching the level-3 anchor rather than level 4.	3 / 5
Progressive Disclosure	Section headers (## Capabilities, ### Marketing Analytics, etc.) give the body navigable structure, but the huge capability catalogs are precisely the content that belongs in separate reference files, and no references exist at all — matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	8 / 20 Passed

Description

66%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.

A serviceable description that covers both what the skill does and when to use it with reasonably natural trigger phrases. Its weaknesses are generic, non-concrete action verbs and a 'when' clause that mirrors the 'what' instead of adding distinct trigger scenarios, plus moderate conflict risk with neighboring analytics/BI skills.

Suggestions

Replace generic verbs with concrete actions, e.g., 'Builds and evaluates predictive models, designs and analyzes A/B tests, performs EDA and statistical inference'.

Differentiate the 'when' clause from the 'what' clause with specific trigger scenarios users would actually say (e.g., 'Use when the user mentions churn, forecasting, segmentation, experiment analysis, or model training').

Narrow the scope terms ('business intelligence', 'data-driven insights') to reduce overlap with visualization and BI-tool skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Expert data scientist') and a few generic actions ('Handles complex data analysis, predictive modeling, and business intelligence') but, unlike the level-4/5 anchors, lists no concrete specific actions — the verbs are domain restatements rather than discrete operations.	3 / 5
Completeness	It answers both 'what' ('Handles complex data analysis, predictive modeling, and business intelligence') and 'when' ('Use for data analysis tasks, ML modeling, statistical analysis, and data-driven insights'), but the 'when' clause largely restates the 'what' rather than giving concrete trigger situations, so it does not reach the explicit level-5 anchor.	4 / 5
Trigger Term Quality	Phrases like 'data analysis tasks, ML modeling, statistical analysis, and data-driven insights' are natural terms users would say, giving good keyword coverage; a few common variations (e.g., forecasting, A/B testing, churn prediction) are missing, keeping it below the comprehensive level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Broad phrases like 'data analysis', 'business intelligence', and 'data-driven insights' create real overlap risk with adjacent skills (visualization, SQL/BI tooling, general analytics), matching 'somewhat specific but could still overlap with similar skills' rather than the mostly-distinct level-4 anchor.	3 / 5
	Total	14 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/data-scientist/SKILL.md
Revision: 2ee2cf7

Reviewed: 3 days ago

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.

data-scientist

Table of Contents

Is this your skill?