data-scientist

Analyze data with hypothesis tests, effect sizes, and confidence intervals.

22|2|Updated Mar 24, 2026

Search Tags:#decision making #hypothesis testing #statistics #analyze #data-quality #effect size #experimental design

Ready to run

npx skills add https://github.com/jshsakura/awesome-opencode-skills --skill data-scientist-jshsakura

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-scientist
Source: https://github.com/jshsakura/awesome-opencode-skills/tree/main/skills/data-scientist
Command: npx skills add https://github.com/jshsakura/awesome-opencode-skills --skill data-scientist-jshsakura

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Data teams often struggle to translate noisy data into credible, action-oriented insights. This Skill provides a disciplined framework for statistical reasoning to support product decisions.

Core Features & Use Cases

Hypothesis-driven analysis with pre-registered evaluation plans.
Experimental design, power calculations, and interpretation of effect sizes.
Actionable recommendations with clearly stated uncertainty and business impact.

Quick Start

Evaluate a new feature using a preregistered hypothesis and report the estimated effect size with confidence interval and recommended next steps.

Frequently Asked Questions about data-scientist

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I design an A/B test with proper statistical power and effect size?▼

To design an A/B test, you must define explicit hypotheses and perform power calculations to determine the required sample size. This skill evaluates experimental design by estimating effect sizes and confidence intervals to ensure credible product analytics.

What is the best way to analyze noisy product data for actionable decisions?▼

Analyzing noisy data for decisions requires a disciplined framework of hypothesis testing and rigorous statistics. This approach translates raw data into actionable recommendations by applying pre-registered evaluation plans and transparently stating uncertainty.

Do I need to define hypotheses before running data quality checks?▼

Yes, you need explicit hypotheses established before analysis to guide rigorous statistical evaluation. Data quality checks are then applied to validate the inputs, ensuring that estimated effect sizes and confidence intervals are credible and reliable.

How do I report uncertainty and business impact from experimental results?▼

Reporting uncertainty from experimental results involves presenting effect sizes with confidence intervals and transparently stating limitations. This skill structures recommendations to clearly connect statistical findings with their business impact and next steps.

Can I use this approach for model evaluation scenarios?▼

Yes, you can use this statistical approach for model evaluation scenarios by applying hypothesis testing to assess performance. It requires data quality checks and transparent uncertainty reporting to generate credible insights for better decisions.