data-scientist

Data Scientist Agent. ML 모델 개발, 실험, 분석을 담당합니다.

Quality

35%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/data-scientist/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description provides a basic role label and high-level responsibilities but lacks the specificity and explicit trigger guidance needed for effective skill selection. The absence of a 'Use when...' clause and concrete action examples significantly weakens its utility in a multi-skill environment.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'train model', 'machine learning', 'predict', 'dataset analysis', 'feature engineering', 'ML pipeline'

Replace generic terms like '분석' with specific concrete actions such as 'train classification/regression models', 'perform EDA', 'tune hyperparameters', 'evaluate model performance'

Include common file types and tools users might mention: '.csv', '.parquet', 'pandas', 'scikit-learn', 'jupyter notebook'

Dimension	Reasoning	Score
Specificity	Names the domain (ML/Data Science) and mentions some actions ('모델 개발, 실험, 분석' - model development, experimentation, analysis), but these are high-level categories rather than concrete specific actions like 'train models', 'evaluate metrics', or 'create visualizations'.	2 / 3
Completeness	Provides a weak 'what' (general ML responsibilities) but completely lacks a 'when' clause or explicit trigger guidance. There is no 'Use when...' statement to help Claude know when to select this skill.	1 / 3
Trigger Term Quality	Contains some relevant keywords like 'ML 모델', 'Data Scientist', '분석' that users might mention, but lacks common variations and natural trigger terms like 'machine learning', 'training', 'prediction', 'dataset', 'feature engineering', or file extensions like '.csv', '.pkl'.	2 / 3
Distinctiveness Conflict Risk	The 'Data Scientist Agent' label provides some distinction, but '분석' (analysis) is very generic and could overlap with many other analytical skills. The description doesn't clearly carve out a unique niche.	2 / 3
	Total	7 / 12 Passed

Implementation

37%

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

This skill content is concise but lacks actionability - it reads as a role description rather than an instructional skill. It tells Claude what a Data Scientist does but provides no concrete guidance on how to perform EDA, develop models, or run experiments. The content would benefit significantly from executable code examples and workflow definitions.

Suggestions

Add concrete code examples for key tasks like EDA (e.g., pandas profiling snippet) and model training (e.g., sklearn pipeline example)

Define a clear workflow for the model development process with validation checkpoints (e.g., data validation -> feature engineering -> model training -> evaluation -> interpretation)

Include specific commands or scripts for experiment tracking and model saving

Add links to detailed guides for complex topics like feature engineering patterns or hyperparameter tuning strategies

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient, listing only essential information without explaining concepts Claude already knows. Every line serves a purpose.	3 / 3
Actionability	The content is entirely descriptive with no concrete code, commands, or executable examples. It describes responsibilities but provides no guidance on how to actually perform any task.	1 / 3
Workflow Clarity	No workflow or process is defined. The skill lists tasks (EDA, model development, tuning) but provides no sequence, steps, or validation checkpoints for any of them.	1 / 3
Progressive Disclosure	The content is well-organized with clear sections and references output locations, but it lacks any links to detailed guides or examples for the complex tasks mentioned.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: shaul1991/shaul-agents-plugin
Commit: 9242c58

Reviewed: 29 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.