Skills data-scientist
📦
data-scientist
Content revision r2 Safe
Analyze Data with Statistical Rigor
Complex data questions can produce unreliable conclusions when methods, assumptions, and business goals are unclear. This skill structures analysis, modeling, validation, and communication into a rigorous workflow.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "data-scientist" from https://skillstore.io/skills/sickn33-data-scientist.md and its manifest at https://skillstore.io/api/skills/sickn33-data-scientist/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "data-scientist". Assess whether a checkout redesign improved conversion.
Expected outcome:
- Primary metric: completed purchases per eligible session.
- Use an intention-to-treat comparison with a confidence interval for the absolute conversion lift.
- Check allocation balance, sample ratio mismatch, exposure logging, novelty effects, and guardrail metrics.
- Report statistical uncertainty and the smallest commercially meaningful lift.
Using "data-scientist". Plan a churn model for a subscription service.
Expected outcome:
- Define churn and the prediction window before selecting features.
- Split data by time and remove information unavailable at prediction time.
- Compare a simple baseline with tree-based models using precision-recall metrics and calibration.
- Monitor feature drift, calibration, subgroup performance, and intervention outcomes after deployment.
Using "data-scientist". Forecast weekly demand for warehouse planning.
Expected outcome:
- Profile trend, seasonality, promotions, stockouts, missing periods, and regional differences.
- Compare seasonal naive, statistical, and feature-based forecasting methods through rolling validation.
- Provide prediction intervals and evaluate inventory costs, not only average forecast error.
Security Audit
Safev5 • 7/23/2026 Open versioned report
The skill contains only instructional Markdown and no executable code, network actions, credential access, or destructive operations. No static or semantic security findings were identified, including no prompt injection language.
1
Files scanned
202
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-data-scientist/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-data-scientist?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-data-scientist?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-data-scientist/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-data-scientist.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
sickn33. (2026). data-scientist security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-data-scientist/audits/5BibTeX citation
@techreport{sickn33-sickn33-data-scientist-2026,
author = {sickn33},
title = {data-scientist security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-data-scientist/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "data-scientist security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-data-scientist/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-data-scientist:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 55
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance
What You Can Build
Evaluate a Product Experiment
Define metrics, estimate sample size, test outcomes, and explain practical significance for a product decision.
Develop a Predictive Model
Plan features, validation, model comparison, interpretability, deployment, and monitoring for a prediction task.
Forecast Operational Demand
Assess seasonality, choose forecasting methods, quantify uncertainty, and connect predictions to inventory decisions.
Try These Prompts
Explore a Dataset
Review [dataset description] for [business goal]. Identify quality issues, useful summaries, visualizations, assumptions, and next analytical steps.
Design an Experiment
Design an experiment for [intervention] and [outcome]. Specify hypotheses, metrics, randomization, sample size inputs, validity risks, and analysis steps.
Plan a Predictive Model
Create a modeling plan for predicting [target] from [available data]. Cover leakage, features, baselines, validation, metrics, interpretation, and monitoring.
Assess Causal Impact
Evaluate the causal effect of [exposure] on [outcome] using [observational data]. Compare identification strategies, assumptions, diagnostics, sensitivity tests, and limitations.
Best Practices
- Define the decision, target population, outcome, and success criteria before choosing methods.
- Validate assumptions, leakage controls, uncertainty estimates, robustness, and subgroup behavior.
- Document data provenance, transformations, parameters, results, limitations, and monitoring requirements.
Avoid
- Do not select a complex model before establishing a relevant baseline.
- Do not interpret correlation, feature importance, or predictive accuracy as causal evidence.
- Do not report a single metric without uncertainty, validation design, and business context.
Frequently Asked Questions
Can this skill analyze my dataset directly?
Yes, when you provide accessible data or representative summaries. Remove sensitive information and explain column meanings, collection methods, and business context.
Which programming languages does it cover?
It covers Python, R, and SQL workflows, plus common analytics, visualization, machine learning, and distributed processing tools.
Can it choose the best machine learning model?
It can recommend and compare candidates. Final selection requires representative validation data, suitable metrics, operational constraints, and error analysis.
Does it support experiment design?
Yes. It can define hypotheses, metrics, randomization, power inputs, analysis plans, validity checks, and reporting requirements.
Can it provide causal conclusions from observational data?
It can assess identification strategies and assumptions. Credible conclusions depend on study design, data quality, diagnostics, and sensitivity analysis.
Does it deploy or monitor models automatically?
No. It can design deployment and monitoring plans, but implementation requires authorized infrastructure, testing, observability, and governance controls.