startup-data-scientist
Data scientist specializing in startup analytics, user behavior tracking, and metrics analysis for Lean Startup and Customer Development methodologies. Use when analyzing user data, setting up analytics, measuring validation metrics, cohort analysis, or when user asks about tracking, metrics, data analysis, or measuring startup hypotheses.
npx skills add majiayu000/claude-skill-registry --skill startup-data-scientist --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill provides data science expertise tailored for startups, focusing on implementing tracking, analyzing user behavior, and delivering actionable metrics and pivot/persevere recommendations. It covers analytics implementation, metrics analysis, hypothesis validation, and data-driven advice, aligning with Lean Startup and Steve Blank methodologies.
How it works
- Analytics Implementation: designs tracking schemas for startup hypotheses, implements event tracking systems, sets up databases for user behavior, creates dashboards for key metrics, and builds data pipelines for analysis.
- Metrics Analysis: computes Lean Startup metrics (AARRR, LTV, CAC, etc.), performs cohort analysis, analyzes retention and churn, conducts statistical significance testing, and performs growth accounting.
- Hypothesis Validation: translates business hypotheses into measurable metrics, designs A/B tests and experiments, analyzes experiment results, provides pivot/persevere recommendations, and conducts customer segmentation analysis.
- Data-Driven Advice: answers questions from lean-startup and steve-blank-adviser skills, provides data to support customer development decisions, identifies patterns in user behavior, predicts unit economics, and forecasts growth and runway.
When to use it
Use when analyzing user data, setting up analytics, measuring validation metrics, conducting cohort analysis, or when users ask about tracking, metrics, data analysis, or measuring startup hypotheses.
What it can touch
The skill declares tools for Read, Write, Edit, Bash, Grep, Glob and leverages claude-code as a declared tool. It prescribes workflows and SQL-like constructs, dashboards, and data pipelines but does not specify executable scripts beyond example code blocks (e.g., JavaScript snippets for tracking and SQL schemas). The explicit touchpoints include event tracking systems, databases, dashboards, and data pipelines.
Caveats
License is MIT. The skill emphasizes quantitative methods and explicit metrics definitions but does not guarantee outcomes. It presents framework-like templates (e.g., acquisition, activation, retention, revenue charts and SQL queries) without claiming guaranteed improvements. It relies on external data sources (databases, dashboards, experiments) for results.
# Startup Data Scientist This skill provides data science expertise specifically for startups following Lean Startup and Steve Blank Customer Development methodologies. It helps implement tracking, analyze user behavior, and provide actionable insights for pivot/persevere decisions. ## Core Philosophy **"In God we trust. All others must bring data."** - W. Edwards Deming For startups, data isn't just nice to have—it's essential for validating hypotheses, making pivot decisions, and finding product/market fit. This skill bridges the gap between methodology and measurement. ## What This Skill Does ### 1. Analytics Implementation - Design tracking schemas for startup hypotheses - Implement event tracking systems - Set up databases for user behavior - Create dashboards for key metrics - Build data pipelines for analysis ### 2. Metrics Analysis - Calculate Lean Startup metrics (AARRR, LTV, CAC, etc.) - Perform cohort analysis - Analyze retention and churn - Statistical significance testing - Growth accounting ### 3. Hypothesis Validation - Translate business hypotheses into measurable metrics - Design A/B tests and experiments - Analyze experiment results - Provide pivot/persevere recom
- Core Philosophy
- What This Skill Does
- 1. Analytics Implementation
- 2. Metrics Analysis
- 3. Hypothesis Validation
- 4. Data-Driven Advice
- Integration with Other Skills
- Part 1: Analytics Architecture
- The Startup Analytics Stack
- Essential Tracking Schema
- Critical Events to Track
- Part 2: Core Metrics Calculation
- Acquisition Metrics
- Activation Metrics
What does the startup-data-scientist skill do?
Data scientist specializing in startup analytics, user behavior tracking, and metrics analysis for Lean Startup and Customer Development methodologies. Use when analyzing user data, setting up analytics, measuring validation metrics, cohort analysis, or when user asks about tracking, metrics, data analysis, or measuring startup hypotheses.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill startup-data-scientist --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.