data-scientist

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

Quality

39%

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-claude/skills/data-scientist/SKILL.md

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

Quality

Content

21%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 skill body is a persona résumé rather than actionable guidance: it enumerates capabilities and tools Claude already knows without providing any executable code, concrete procedures, or validation checkpoints. Section structure exists but the bulk content that belongs in reference files is inlined, hurting token efficiency and progressive disclosure.

Suggestions

Replace the capability/tool enumerations with concrete, copy-paste-ready workflows (e.g. an end-to-end churn-modeling or A/B-test-analysis template with real code) to raise actionability.

Move the long lists of algorithms, libraries, and domain applications into separate reference files under references/ and link to them from a lean SKILL.md overview, improving both conciseness and progressive disclosure.

Add explicit validation checkpoints and error-recovery feedback loops to the Response Approach steps (e.g. 'validate model assumptions, check for data leakage, re-run if drift detected') so the workflow is sequenced with real checkpoints.

Dimension	Reasoning	Score
Conciseness	The ~190-line body exhaustively enumerates algorithms, libraries, and methods Claude already knows (XGBoost, LightGBM, ARIMA, Prophet, SHAP, LIME, etc.), which is heavily padded; it is not prose explanations of basics so it sits above level 1, but the bulk is redundant enumeration that does not earn its tokens.	2 / 5
Actionability	There is no executable code, no commands, and no concrete procedure; the body only describes a persona and its capabilities ('Supervised learning: linear/logistic regression...', 'Provide actionable steps and verification'), matching the 'entirely vague or abstract; only describes rather than instructs' anchor.	1 / 5
Workflow Clarity	The 'Response Approach' gives a rough 8-step sequence but the steps are abstract ('Understand business context', 'Explore data thoroughly') with no concrete commands, no validation checkpoints, and no error-recovery feedback loops, matching the 'rough sequence present but many gaps; validation absent' anchor.	2 / 5
Progressive Disclosure	The body uses clear ## / ### section headers for organization, but no bundle files exist and the large capability/domain enumerations that clearly belong in separate reference files are inlined entirely, so it lands at 'some structure but content that should be separate is inline'.	3 / 5
	Total	8 / 20 Passed

Description

57%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 clearly states what the skill covers but omits any explicit 'Use when...' trigger guidance, which caps its completeness. Trigger terms are natural and reasonably well covered, though specificity and distinctiveness are only moderate because the stated actions are broad capability categories rather than concrete, narrowly-scoped tasks.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user needs predictive modeling, A/B test analysis, forecasting, or statistical analysis of a dataset.'

Replace abstract capability categories with concrete actions (e.g. 'build churn/forecasting models, run and analyze A/B tests, segment customers') to raise specificity and distinctiveness.

Narrow the scope or add distinguishing triggers so it does not collide with general ML or BI skills.

Dimension	Reasoning	Score
Specificity	Names the data-science domain and lists several broad action areas ('advanced analytics, machine learning, and statistical modeling', 'predictive modeling, and business intelligence'), but these are abstract capability categories rather than concrete actions, so it sits at the 'names domain and a few actions but not comprehensive' anchor rather than the more concrete level 4.	3 / 5
Completeness	It has a clear 'what' (an expert data scientist for analytics/ML/modeling) but no explicit 'when' / 'Use when...' trigger clause, and per the rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would actually say ('data scientist', 'machine learning', 'statistical modeling', 'data analysis', 'predictive modeling', 'business intelligence') with good coverage; a few common synonyms (e.g. forecasting, A/B testing) are absent, keeping it just below level 5.	4 / 5
Distinctiveness Conflict Risk	'Data scientist' is a recognizable niche, but the breadth ('advanced analytics, machine learning, statistical modeling, business intelligence') creates real overlap with general ML/analytics skills, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	13 / 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-claude/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.